You can find a list of completed Phd theses here.
2022
Perevalov, Aleksandr; Yan, Xi; Kovriguina, Liubov; Jiang, Longquan; Both, Andreas; Usbeck, Ricardo
Knowledge Graph Question Answering Leaderboard: A Community Resource to Prevent a Replication Crisis Journal Article
In: CoRR, vol. abs/2201.08174, 2022.
@article{DBLP:journals/corr/abs-2201-08174,
title = {Knowledge Graph Question Answering Leaderboard: A Community Resource
to Prevent a Replication Crisis},
author = {Aleksandr Perevalov and
Xi Yan and
Liubov Kovriguina and
Longquan Jiang and
Andreas Both and
Ricardo Usbeck},
url = {https://arxiv.org/abs/2201.08174},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2201.08174},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Xiong, Bo; Potyka, Nico; Tran, Trung-Kien; Nayyeri, Mojtaba; Staab, Steffen
Box Embeddings for the Description Logic EL++ Journal Article
In: CoRR, vol. abs/2201.09919, 2022.
@article{DBLP:journals/corr/abs-2201-09919,
title = {Box Embeddings for the Description Logic EL++},
author = {Bo Xiong and
Nico Potyka and
Trung-Kien Tran and
Mojtaba Nayyeri and
Steffen Staab},
url = {https://arxiv.org/abs/2201.09919},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2201.09919},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Moghaddam, Farshad Bakhshandegan; Lehmann, Jens; Jabeen, Hajira
DistAD: A Distributed Generic Anomaly Detection Framework over Large KGs Inproceedings
In: 16th IEEE International Conference on Semantic Computing, ICSC 2022, Laguna Hills, CA, USA, January 26-28, 2022, pp. 243–250, IEEE, 2022.
@inproceedings{DBLP:conf/semco/MoghaddamLJ22,
title = {DistAD: A Distributed Generic Anomaly Detection Framework over Large
KGs},
author = {Farshad Bakhshandegan Moghaddam and
Jens Lehmann and
Hajira Jabeen},
url = {https://doi.org/10.1109/ICSC52841.2022.00047},
doi = {10.1109/ICSC52841.2022.00047},
year = {2022},
date = {2022-01-01},
booktitle = {16th IEEE International Conference on Semantic Computing, ICSC
2022, Laguna Hills, CA, USA, January 26-28, 2022},
pages = {243--250},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Perevalov, Aleksandr; Diefenbach, Dennis; Usbeck, Ricardo; Both, Andreas
QALD-9-plus: A Multilingual Dataset for Question Answering over DBpedia and Wikidata Translated by Native Speakers Inproceedings
In: 16th IEEE International Conference on Semantic Computing, ICSC 2022, Laguna Hills, CA, USA, January 26-28, 2022, pp. 229–234, IEEE, 2022.
@inproceedings{DBLP:conf/semco/PerevalovDUB22,
title = {QALD-9-plus: A Multilingual Dataset for Question Answering over
DBpedia and Wikidata Translated by Native Speakers},
author = {Aleksandr Perevalov and
Dennis Diefenbach and
Ricardo Usbeck and
Andreas Both},
url = {https://doi.org/10.1109/ICSC52841.2022.00045},
doi = {10.1109/ICSC52841.2022.00045},
year = {2022},
date = {2022-01-01},
booktitle = {16th IEEE International Conference on Semantic Computing, ICSC
2022, Laguna Hills, CA, USA, January 26-28, 2022},
pages = {229--234},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Xu, Chengjin; Nayyeri, Mojtaba; Chen, Yung-Yu; Lehmann, Jens
Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion Journal Article
In: CoRR, vol. abs/2202.09464, 2022.
@article{DBLP:journals/corr/abs-2202-09464,
title = {Geometric Algebra based Embeddings for Static and Temporal Knowledge
Graph Completion},
author = {Chengjin Xu and
Mojtaba Nayyeri and
Yung-Yu Chen and
Jens Lehmann},
url = {https://arxiv.org/abs/2202.09464},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2202.09464},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Xu, Chengjin; Su, Fenglong; Lehmann, Jens
Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs Journal Article
In: CoRR, vol. abs/2203.02150, 2022.
@article{DBLP:journals/corr/abs-2203-02150,
title = {Time-aware Graph Neural Networks for Entity Alignment between Temporal
Knowledge Graphs},
author = {Chengjin Xu and
Fenglong Su and
Jens Lehmann},
url = {https://doi.org/10.48550/arXiv.2203.02150},
doi = {10.48550/arXiv.2203.02150},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2203.02150},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Alam, Mirza Mohtashim; Rony, Md. Rashad Al Hasan; Ali, Semab; Lehmann, Jens; Vahdati, Sahar
Language Model-driven Negative Sampling Journal Article
In: CoRR, vol. abs/2203.04703, 2022.
@article{DBLP:journals/corr/abs-2203-04703,
title = {Language Model-driven Negative Sampling},
author = {Mirza Mohtashim Alam and
Md. Rashad Al Hasan Rony and
Semab Ali and
Jens Lehmann and
Sahar Vahdati},
url = {https://doi.org/10.48550/arXiv.2203.04703},
doi = {10.48550/arXiv.2203.04703},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2203.04703},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Rony, Md. Rashad Al Hasan; Kovriguina, Liubov; Chaudhuri, Debanjan; Usbeck, Ricardo; Lehmann, Jens
RoMe: A Robust Metric for Evaluating Natural Language Generation Journal Article
In: CoRR, vol. abs/2203.09183, 2022.
@article{DBLP:journals/corr/abs-2203-09183,
title = {RoMe: A Robust Metric for Evaluating Natural Language Generation},
author = {Md. Rashad Al Hasan Rony and
Liubov Kovriguina and
Debanjan Chaudhuri and
Ricardo Usbeck and
Jens Lehmann},
url = {https://doi.org/10.48550/arXiv.2203.09183},
doi = {10.48550/arXiv.2203.09183},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2203.09183},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Reimann, Lars; Kniesel-Wünsche, Günter
Improving the Learnability of Machine Learning APIs by Semi-Automated API Wrapping Journal Article
In: CoRR, vol. abs/2203.15491, 2022.
@article{DBLP:journals/corr/abs-2203-15491,
title = {Improving the Learnability of Machine Learning APIs by Semi-Automated
API Wrapping},
author = {Lars Reimann and
Günter Kniesel-Wünsche},
url = {https://doi.org/10.48550/arXiv.2203.15491},
doi = {10.48550/arXiv.2203.15491},
year = {2022},
date = {2022-01-01},
journal = {CoRR},
volume = {abs/2203.15491},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Westphal, Patrick; Grubenmann, Tobias; Collarana, Diego; Bin, Simon; Bühmann, Lorenz; Lehmann, Jens
Spatial concept learning and inference on geospatial polygon data Journal Article
In: Knowl. Based Syst., vol. 241, pp. 108233, 2022.
@article{DBLP:journals/kbs/WestphalGCBB022,
title = {Spatial concept learning and inference on geospatial polygon data},
author = {Patrick Westphal and
Tobias Grubenmann and
Diego Collarana and
Simon Bin and
Lorenz Bühmann and
Jens Lehmann},
url = {https://doi.org/10.1016/j.knosys.2022.108233},
doi = {10.1016/j.knosys.2022.108233},
year = {2022},
date = {2022-01-01},
journal = {Knowl. Based Syst.},
volume = {241},
pages = {108233},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Han, Xiaolin; Aglio, Daniele Dell'; Grubenmann, Tobias; Cheng, Reynold; Bernstein, Abraham
A framework for differentially-private knowledge graph embeddings Journal Article
In: J. Web Semant., vol. 72, pp. 100696, 2022.
@article{DBLP:journals/ws/HanDGCB22,
title = {A framework for differentially-private knowledge graph embeddings},
author = {Xiaolin Han and
Daniele Dell' Aglio and
Tobias Grubenmann and
Reynold Cheng and
Abraham Bernstein},
url = {https://doi.org/10.1016/j.websem.2021.100696},
doi = {10.1016/j.websem.2021.100696},
year = {2022},
date = {2022-01-01},
journal = {J. Web Semant.},
volume = {72},
pages = {100696},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2021
Musyaffa, Fathoni Arief
Comparative Analysis of Open Linked Fiscal Data PhD Thesis
Rheinische Friedrich-Wilhelms-Universität Bonn, 2021.
@phdthesis{Musyaffa2021,
title = {Comparative Analysis of Open Linked Fiscal Data},
author = {Fathoni Arief Musyaffa},
url = {https://bonndoc.ulb.uni-bonn.de/xmlui/handle/20.500.11811/9114},
year = {2021},
date = {2021-06-01},
school = {Rheinische Friedrich-Wilhelms-Universität Bonn},
abstract = {The open data movement within public administrations has provided data regarding governance publicly. As public administrators and governments produce data and release the data as open data, the volume of the data is highly increasing. One of these datasets is budget and spending data, which has been gaining interest to the extent that several working groups and CSO/NGOs started working on this particular open data domain. The majority of these datasets are part of the open budget and spending datasets, which laid out data regarding how public administrations plan, revise, allocate, and expense their governance funding. The disclosure of public administration budget and spending data is expected to improve governance transparency, accountability, law enforcement, and political participation.
Unfortunately, the analysis of budget and spending datasets is not a trivial task to do for several reasons. First, the quality of open fiscal data varies. Standards and recommendations for publishing open data are available, however, these standards are often not met and no framework specifically addresses fiscal data quality measurements. Second, the datasets are heterogeneous, since it is produced by different public administrations with different business process, accounting practice, requirements, and language. This lead to a challenging task in data integration across public budget and spending data. The structural and linguistic heterogeneity of open budget and spending data makes comparative analysis across datasets difficult to perform. Third, datasets within the budget and spending domain are complicated. To be able to comprehend such data, expertise is needed both from the public accounting/budgeting domain, as well as the technical domain to digest the datasets properly. Fourth, a platform to transform, store, analyze, and visualize datasets is necessary, especially those that make the utilization of semantic analysis is possible. Fifth, there is no conceptual association between datasets, which can be used as a comparison point to analyze fiscal records between compared public administrations. Lastly, there is a lack of methodology to consume and compare linked open fiscal data records across different public administrations.
Our focus in this thesis is hence to perform research to help the community gain a better understanding of open fiscal data, provide analysis of their quality, suggest a way to publish open fiscal data in an improved manner, analyze the open fiscal data heterogeneity while also laying out lessons learned regarding their current state and supporting data formats that are capable for open fiscal data integration. Consequently, a platform to digest, analyze and visualize these datasets is devised, continued with performing experiments on multilingual fiscal data concept mapping and wrapped up with a proof-of-concept description of comparative analysis over linked open fiscal data.
},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Unfortunately, the analysis of budget and spending datasets is not a trivial task to do for several reasons. First, the quality of open fiscal data varies. Standards and recommendations for publishing open data are available, however, these standards are often not met and no framework specifically addresses fiscal data quality measurements. Second, the datasets are heterogeneous, since it is produced by different public administrations with different business process, accounting practice, requirements, and language. This lead to a challenging task in data integration across public budget and spending data. The structural and linguistic heterogeneity of open budget and spending data makes comparative analysis across datasets difficult to perform. Third, datasets within the budget and spending domain are complicated. To be able to comprehend such data, expertise is needed both from the public accounting/budgeting domain, as well as the technical domain to digest the datasets properly. Fourth, a platform to transform, store, analyze, and visualize datasets is necessary, especially those that make the utilization of semantic analysis is possible. Fifth, there is no conceptual association between datasets, which can be used as a comparison point to analyze fiscal records between compared public administrations. Lastly, there is a lack of methodology to consume and compare linked open fiscal data records across different public administrations.
Our focus in this thesis is hence to perform research to help the community gain a better understanding of open fiscal data, provide analysis of their quality, suggest a way to publish open fiscal data in an improved manner, analyze the open fiscal data heterogeneity while also laying out lessons learned regarding their current state and supporting data formats that are capable for open fiscal data integration. Consequently, a platform to digest, analyze and visualize these datasets is devised, continued with performing experiments on multilingual fiscal data concept mapping and wrapped up with a proof-of-concept description of comparative analysis over linked open fiscal data.
Mousavinezhad, Najmeh
Knowledge Extraction Methods for the Analysis of Contractual Agreements PhD Thesis
Rheinische Friedrich-Wilhelms-Universität Bonn, 2021.
@phdthesis{,
title = {Knowledge Extraction Methods for the Analysis of Contractual Agreements},
author = {Najmeh Mousavinezhad},
url = {https://nbn-resolving.org/urn:nbn:de:hbz:5-64537},
year = {2021},
date = {2021-05-31},
urldate = {2021-05-31},
school = {Rheinische Friedrich-Wilhelms-Universität Bonn},
abstract = {The ubiquitous availability of the Internet results in a massive number of apps, software, and online services with accompanying contractual agreements in the form of end-user license agreement' andprivacy policy’. Often the textual documents describing rights, policies, and conditions comprise many pages and can not be reasonably assumed to be read and understood by humans. Although everyone is exposed to such consent forms, the majority tend to ignore them due to their length and complexity. However, the cost of ignoring terms and conditions is not always negligible, and occasionally people have to pay (money or other means) as a result of their oversight. In this thesis, we focus on the interpretation of contractual agreements for the benefit of end-users. Contractual agreements encompass both the privacy policies and the general terms and conditions related to software and services. The main characteristics of such agreements are their use of legal terminologies and limited vocabulary. This feature has pros and cons. On one hand, the clear structure and legal language facilitate the mapping between the human-readable agreements and machine-processable concepts. On the other hand, the legal terminologies make the contractual agreement complex, subjective, and, therefore, open to interpretation. This thesis addresses the problem of contractual agreement analysis from both perspectives. In order to provide a structured presentation of contractual agreements, we apply text mining and semantic technologies to develop approaches that extract important information from the agreements and retrieve helpful links and resources for better comprehension. Our approaches are based on ontology-based information extraction, machine learning, and semantic similarity and aim to deliver tedious consent forms in a user friendly and visualized format. The ontology-based information extraction approach processes the human-readable license agreement guided by a domain ontology to extract deontic modalities and presents a summarized output to the end-user. In the extraction phase, we focus on three key rights and conditions: permission, prohibition, duty and cluster the extracted excerpts according to their similarities. The clustering is based on semantic similarity employing a distributional semantics approach on large word embeddings database. The machine learning method employs deep neural networks to classify a privacy policy’s paragraphs into pre-defined categories. Since the prediction results of the trained model are promising, we further use the predicted classes to assign five risk colors (Green, Yellow, Red) to five privacy icons (Expected Use, Expected Collection, Precise Location, Data Retention and Children Privacy). Furthermore, given that any contractual agreement must comply with the relevant legislation, we utilize text semantic similarity to map an agreement’s content to regulatory documents. The semantic similarity-based approach finds candidate sentences in an agreement that are potentially related to specific articles in the regulation. Then, for each candidate sentence, the relevant article and provision is found according to their semantic similarity. The achieved results from our proposed approaches allow us to conclude that although semi-automatic approaches lead to information loss, they save time and effort by producing instant results and facilitate the end-users understanding of legal texts.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Fathalla, Said
Towards Facilitating Scholarly Communication using Semantic Technologies PhD Thesis
Rheinische Friedrich-Wilhelms-Universität Bonn, 2021.
@phdthesis{said_thesis,
title = {Towards Facilitating Scholarly Communication using Semantic Technologies},
author = {Said Fathalla},
url = {https://hdl.handle.net/20.500.11811/9089},
year = {2021},
date = {2021-05-20},
school = {Rheinische Friedrich-Wilhelms-Universität Bonn},
abstract = {Web technologies have substantially stimulated the submission of manuscripts, publishing scientific articles, as well as the organization of scholarly events, especially virtual events, when a global crisis occurs, which consequently restricts travels across the globe. Publication in scholarly events, such as conferences, workshops, and symposiums, is essential and pervasive in computer science, engineering, and natural sciences. The past years have witnessed significant growth in scholarly data published on the Web, mostly in unstructured formats, which immolate the embedded semantics and relationships between various entities. These formats restrict the reusability of the data, i.e., data analysis, retrieval, and mining. Therefore, managing, retrieving, and analyzing such data have become quite challenging. Consequently, there is a pressing need to represent this data in a semantic format, i.e., Linked Data, which significantly improves scholarly communication by supporting researchers concerning analyzing, retrieving, and exploring scholarly data. Notwithstanding the considerable advances in technology, publishing and exchanging scholarly data have not substantially changed (i.e., still follows the document-based scheme), thus restricting both developments of research applications in various industries as well as data preservation and exploration. This thesis tackles the problem of facilitating scholarly communication using semantic technologies. The ultimate aim is improving scholarly communication by facilitating the transformation from a document-based to knowledge-based scholarly communication, which helps researchers to examine science itself with a new perspective. Key steps towards the goal have been taken by proposing methodologies as well as a metrics suite for publishing and assessing the quality of scholarly events concerning several criteria, in particular, Computer Science as well as Physics, Mathematics, and Engineering. Within the framework of these criteria, steps towards assessing the quality of scholarly events and recommendations to various stakeholders have been taken. Furthermore, we engineered the Scientific Events Ontology in order to enable the enriched semantic representation of scholarly event metadata. Currently, this ontology is in use on thousands of OpenResearch.org events wiki pages. These steps will have far-reaching implications for the various stakeholders involved in the scholarly communication domain, including authors, sponsors, reviewers, publishers, and libraries. Most of the scholarly data publishers, such as Springer Nature, have taken serious steps towards publishing research data in a semantic form by publishing collated information from across the research landscape, such as research articles, scholarly events, persons, and grants, as knowledge graphs. Interlinking this data will significantly enable the provision of better and more intelligent services for the discovery of scientific work, which opens new opportunities for both scholarly data exploration and analysis. In the direction to this goal, we proposed the Science Knowledge Graph Ontologies suite, which comprises four OWL ontologies for representing the scientific knowledge in various fields of science, including Computer Science, Physics, and Pharmaceutical science. Besides, we developed an upper ontology on top of them for modeling modern science branches and related concepts, such as scientific discovery, instruments, and phenomena.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Dubey, Mohnish
Towards Complex Question Answering over Knowledge Graphs PhD Thesis
University of Bonn , 2021.
@phdthesis{mohnishthesis,
title = {Towards Complex Question Answering over Knowledge Graphs},
author = {Mohnish Dubey},
url = {https://bonndoc.ulb.uni-bonn.de/xmlui/handle/20.500.11811/9122},
year = {2021},
date = {2021-01-19},
school = {University of Bonn },
abstract = {Over the past decade, Knowledge Graphs (KG) have emerged as a prominent repository for storing facts about the world in a linked data architecture. Providing machines with the capability of exploring such Knowledge Graphs and answering natural language questions over them, has been an active area of research. The purpose of this work, is to delve further into the research of retrieving information stored in KGs, based on the natural language questions posed by the user. Knowledge Graph Question Answering (KGQA) aims to produce a concise answer to a user question, such that the user is exempt from using KG vocabulary and overheads of learning a formal query language. Existing KGQA systems have achieved excellent results over Simple Questions, where the information required is limited to a single triple and a single formal query pattern. Our motivation is to improve the performance of KGQA over Complex Questions, where formal query patterns significantly vary, and a single triple is not confining for all the required information. Complex KGQA provides several challenges such as understanding semantics and syntactic structure of questions, Entity Linking, Relation Linking and Answer Representation. Lack of suitable datasets for complex question answering further adds to research gaps. Hence, in this thesis, we focus the research objective of laying the foundations for the advancement of the state-of-the-art for Complex Question Answering over Knowledge Graphs, by providing techniques to solve various challenges and provide resources to fill the research gaps.
First, we propose Normalized Query Structure (NQS), which is a linguistic analyzer module that helps the QA system to detect inputs and intents and the relation between them in the users’ question. NQS acts like an intermediate language between natural language questions and formal expressions to ease the process of query formulation for complex questions. We then developed a framework named LC-QuAD to generate large scale question answering dataset by reversing the process of question answering, thereby translating natural language questions from the formal query using intermediate templates. Our goal is to use this framework for high variations in the query patterns and create a large size dataset with minimum human effort. The first version of the dataset consists of 5,000 complex questions. By extending the LC-QuAD framework to support Reified KGs and crowd-sourcing, we published the second version of the dataset as LC-QuAD 2.0, consisting of 30,000 questions with their paraphrases and has higher complexity and new variations in the questions. To overcome the problem of Entity Linking and Relation Linking in KGQA, we develop EARL, a module performing these two tasks as a single joint task for complex question answering. We develop approaches for this module, first by formalizing the task as an instance of the Generalized Traveling Salesman Problem (GTSP) and the second approach uses machine learning to exploit the connection density between nodes in the Knowledge Graph. Lastly, we create another large scale dataset to answer verbalization and provide results for multiple baseline systems on it. The Verbalization dataset is introduced to make the system’s response more human-like. The NQS based KGQA system was next to the best system in terms of accuracy on the QALD-5 dataset. We empirically prove that NQS is robust to tackle paraphrases of the questions. EARL achieves the state of the art results in Entity Linking and Relation Linking for question answering on several KGQA datasets. The dataset curated in this thesis has helped the research community to move forward in the direction of improving the accuracy of complex question answering as a task as other researchers too developed several KGQA systems and modules around these published datasets. With the large-scale datasets, we have encouraged the use of large scale machine learning, deep learning and emergence of new techniques to advance the state-of-the-art in complex question answering over knowledge graphs. We further developed core components for the KGQA pipeline to overcome the challenges of Question Understanding, Entity-Relation Linking and Answer Verbalization and thus achieve our research objective. All the proposed approaches mentioned in this thesis and the published resources are available at https://github.com/AskNowQA and are released under the umbrella project AskNow.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
First, we propose Normalized Query Structure (NQS), which is a linguistic analyzer module that helps the QA system to detect inputs and intents and the relation between them in the users’ question. NQS acts like an intermediate language between natural language questions and formal expressions to ease the process of query formulation for complex questions. We then developed a framework named LC-QuAD to generate large scale question answering dataset by reversing the process of question answering, thereby translating natural language questions from the formal query using intermediate templates. Our goal is to use this framework for high variations in the query patterns and create a large size dataset with minimum human effort. The first version of the dataset consists of 5,000 complex questions. By extending the LC-QuAD framework to support Reified KGs and crowd-sourcing, we published the second version of the dataset as LC-QuAD 2.0, consisting of 30,000 questions with their paraphrases and has higher complexity and new variations in the questions. To overcome the problem of Entity Linking and Relation Linking in KGQA, we develop EARL, a module performing these two tasks as a single joint task for complex question answering. We develop approaches for this module, first by formalizing the task as an instance of the Generalized Traveling Salesman Problem (GTSP) and the second approach uses machine learning to exploit the connection density between nodes in the Knowledge Graph. Lastly, we create another large scale dataset to answer verbalization and provide results for multiple baseline systems on it. The Verbalization dataset is introduced to make the system’s response more human-like. The NQS based KGQA system was next to the best system in terms of accuracy on the QALD-5 dataset. We empirically prove that NQS is robust to tackle paraphrases of the questions. EARL achieves the state of the art results in Entity Linking and Relation Linking for question answering on several KGQA datasets. The dataset curated in this thesis has helped the research community to move forward in the direction of improving the accuracy of complex question answering as a task as other researchers too developed several KGQA systems and modules around these published datasets. With the large-scale datasets, we have encouraged the use of large scale machine learning, deep learning and emergence of new techniques to advance the state-of-the-art in complex question answering over knowledge graphs. We further developed core components for the KGQA pipeline to overcome the challenges of Question Understanding, Entity-Relation Linking and Answer Verbalization and thus achieve our research objective. All the proposed approaches mentioned in this thesis and the published resources are available at https://github.com/AskNowQA and are released under the umbrella project AskNow.
Oliveira, Italo Lopes; Fileto, Renato; Speck, René; Garcia, Lu'is Paulo F.; Moussallem, Diego; Lehmann, Jens
Towards holistic Entity Linking: Survey and directions Journal Article
In: Inf. Syst., vol. 95, pp. 101624, 2021.
@article{DBLP:journals/is/OliveiraFSGML21,
title = {Towards holistic Entity Linking: Survey and directions},
author = {Italo Lopes Oliveira and
Renato Fileto and
René Speck and
Lu{'i}s Paulo F. Garcia and
Diego Moussallem and
Jens Lehmann},
url = {https://doi.org/10.1016/j.is.2020.101624},
doi = {10.1016/j.is.2020.101624},
year = {2021},
date = {2021-01-01},
journal = {Inf. Syst.},
volume = {95},
pages = {101624},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mami, Mohamed Nadjib
Strategies for a Semantified Uniform Access to Large and Heterogeneous Data Sources PhD Thesis
Rheinische Friedrich-Wilhelms-Universität Bonn, 2021.
@phdthesis{handle:20.500.11811/8925,
title = {Strategies for a Semantified Uniform Access to Large and Heterogeneous Data Sources},
author = {Mohamed Nadjib Mami},
url = {http://hdl.handle.net/20.500.11811/8925},
year = {2021},
date = {2021-01-01},
school = {Rheinische Friedrich-Wilhelms-Universität Bonn},
abstract = {The remarkable advances achieved in both research and development of Data Management as well as the prevalence of high-speed Internet and technology in the last few decades have caused unprecedented data avalanche. Large volumes of data manifested in a multitude of types and formats are being generated and becoming the new norm. In this context, it is crucial to both leverage existing approaches and propose novel ones to overcome this data size and complexity, and thus facilitate data exploitation. In this thesis, we investigate two major approaches to addressing this challenge: Physical Data Integration and Logical Data Integration. The specific problem tackled is to enable querying large and heterogeneous data sources in an ad hoc manner.
In the Physical Data Integration, data is physically and wholly transformed into a canonical unique format, which can then be directly and uniformly queried. In the Logical Data Integration, data remains in its original format and form and a middleware is posed above the data allowing to map various schemata elements to a high-level unifying formal model. The latter enables the querying of the underlying original data in an ad hoc and uniform way, a framework which we call Semantic Data Lake, SDL. Both approaches have their advantages and disadvantages. For example, in the former, a significant effort and cost are devoted to pre-processing and transforming the data to the unified canonical format. In the latter, the cost is shifted to the query processing phases, e.g., query analysis, relevant source detection and results reconciliation.
In this thesis we investigate both directions and study their strengths and weaknesses. For each direction, we propose a set of approaches and demonstrate their feasibility via a proposed implementation. In both directions, we appeal to Semantic Web technologies, which provide a set of time-proven techniques and standards that are dedicated to Data Integration. In the Physical Integration, we suggest an end-to-end blueprint for the semantification of large and heterogeneous data sources, i.e., physically transforming the data to the Semantic Web data standard RDF (Resource Description Framework). A unified data representation, storage and query interface over the data are suggested. In the Logical Integration, we provide a description of the SDL architecture, which allows querying data sources right on their original form and format without requiring a prior transformation and centralization. For a number of reasons that we detail, we put more emphasis on the virtual approach. We present the effort behind an extensible implementation of the SDL, called Squerall, which leverages state-of-the-art Semantic and Big Data technologies, e.g., RML (RDF Mapping Language) mappings, FnO (Function Ontology) ontology, and Apache Spark. A series of evaluation is conducted to evaluate the implementation along with various metrics and input data scales. In particular, we describe an industrial real-world use case using our SDL implementation. In a preparation phase, we conduct a survey for the Query Translation methods in order to back some of our design choices.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
In the Physical Data Integration, data is physically and wholly transformed into a canonical unique format, which can then be directly and uniformly queried. In the Logical Data Integration, data remains in its original format and form and a middleware is posed above the data allowing to map various schemata elements to a high-level unifying formal model. The latter enables the querying of the underlying original data in an ad hoc and uniform way, a framework which we call Semantic Data Lake, SDL. Both approaches have their advantages and disadvantages. For example, in the former, a significant effort and cost are devoted to pre-processing and transforming the data to the unified canonical format. In the latter, the cost is shifted to the query processing phases, e.g., query analysis, relevant source detection and results reconciliation.
In this thesis we investigate both directions and study their strengths and weaknesses. For each direction, we propose a set of approaches and demonstrate their feasibility via a proposed implementation. In both directions, we appeal to Semantic Web technologies, which provide a set of time-proven techniques and standards that are dedicated to Data Integration. In the Physical Integration, we suggest an end-to-end blueprint for the semantification of large and heterogeneous data sources, i.e., physically transforming the data to the Semantic Web data standard RDF (Resource Description Framework). A unified data representation, storage and query interface over the data are suggested. In the Logical Integration, we provide a description of the SDL architecture, which allows querying data sources right on their original form and format without requiring a prior transformation and centralization. For a number of reasons that we detail, we put more emphasis on the virtual approach. We present the effort behind an extensible implementation of the SDL, called Squerall, which leverages state-of-the-art Semantic and Big Data technologies, e.g., RML (RDF Mapping Language) mappings, FnO (Function Ontology) ontology, and Apache Spark. A series of evaluation is conducted to evaluate the implementation along with various metrics and input data scales. In particular, we describe an industrial real-world use case using our SDL implementation. In a preparation phase, we conduct a survey for the Query Translation methods in order to back some of our design choices.
Thakker, Harsh Vrajeshkumar
On Supporting Interoperability between RDF and Property Graph Databases PhD Thesis
Rheinische Friedrich-Wilhelms-Universität Bonn, 2021.
@phdthesis{handle:20.500.11811/9083,
title = {On Supporting Interoperability between RDF and Property Graph Databases},
author = {Harsh Vrajeshkumar Thakker},
url = {http://hdl.handle.net/20.500.11811/9083},
year = {2021},
date = {2021-01-01},
school = {Rheinische Friedrich-Wilhelms-Universität Bonn},
abstract = {Over the last few years, the amount and availability of machine-readable Open, Linked, and Big data on the web has increased. Simultaneously, several data management systems have emerged to deal with the increased amounts of this structured data. RDF and Graph databases are two popular approaches for data management based on modeling, storing, and querying graph-like data. RDF database systems are based on the W3C standard RDF data model and use the W3C standard SPARQL as their defacto query language. Most graph database systems are based on the Property Graph (PG) data model and use the Gremlin language as their query language due to its popularity amongst vendors. Given that both of these approaches have distinct and complementary characteristics – RDF is suited for distributed data integration with built-in world-wide unique identifiers and vocabularies; PGs, on the other hand, support horizontally scalable storage and querying, and are widely used for modern data analytics applications, – it becomes necessary to support interoperability amongst them. The main objective of this dissertation is to study and address this interoperability issue. We identified three research challenges that are concerned with the data interoperability, query interoperability, and benchmarking of these databases. First, we tackle the data interoperability problem. We propose three direct mappings (schema-dependent and schema-independent) for transforming an RDF database into a property graph database. We show that the proposed mappings satisfy the desired properties of semantics preservation and information preservation. Based on our analysis (both formal and empirical), we argue that any RDF database can be transformed into a PG database using our approach. Second, we propose a novel approach for querying PG databases using SPARQL using Gremlin traversals – GREMLINATOR to tackle the query interoperability problem. In doing so, we first formalize the declarative constructs of Gremlin language using a consolidated graph relational algebra and define mappings to translate SPARQL queries into Gremlin traversals. GREMLINATOR has been officially integrated as a plugin for the Apache TinkerPop graph computing framework (as sparql-gremlin), which enables users to execute SPARQL queries over a wide variety of OLTP graph databases and OLAP graph processing frameworks. Finally, we tackle the third, benchmarking (performance evaluation), problem. We propose a novel framework – LITMUS Benchmark Suite that allows a choke-point driven performance comparison and analysis of various databases (PG and RDF-based) using various third-party real and synthetic datasets and queries. We also studied a variety of intrinsic and extrinsic factors – data and system-specific metrics and Key Performance Indicators (KPIs) that influence a given system’s performance. LITMUS incorporates various memory, processor, data quality, indexing, query typology, and data-based metrics for providing a fine-grained evaluation of the benchmark. In conclusion, by filling the research gaps, addressed by this dissertation, we have laid a solid formal and practical foundation for supporting interoperability between the RDF and Property graph database technology stacks. The artifacts produced during the term of this dissertation have been integrated into various academic and industrial projects.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Nayyeri, Mojtaba; Vahdati, Sahar; Aykul, Can; Lehmann, Jens
5ast Knowledge Graph Embeddings with Projective Transformations Inproceedings
In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp. 9064–9072, AAAI Press, 2021.
@inproceedings{DBLP:conf/aaai/NayyeriVA021,
title = {5ast Knowledge Graph Embeddings with Projective Transformations},
author = {Mojtaba Nayyeri and
Sahar Vahdati and
Can Aykul and
Jens Lehmann},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/17095},
year = {2021},
date = {2021-01-01},
booktitle = {Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9,
2021},
pages = {9064--9072},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Guluzade, Aynur; Kacupaj, Endri; Maleshkova, Maria
Demographic Aware Probabilistic Medical Knowledge Graph Embeddings of Electronic Medical Records Inproceedings
In: Artificial Intelligence in Medicine - 19th International Conference on Artificial Intelligence in Medicine, AIME 2021, Virtual Event, June 15-18, 2021, Proceedings, pp. 408–417, Springer, 2021.
@inproceedings{DBLP:conf/aime/GuluzadeKM21,
title = {Demographic Aware Probabilistic Medical Knowledge Graph Embeddings of Electronic Medical Records},
author = {Aynur Guluzade and
Endri Kacupaj and
Maria Maleshkova},
url = {https://doi.org/10.1007/978-3-030-77211-6_48},
doi = {10.1007/978-3-030-77211-6_48},
year = {2021},
date = {2021-01-01},
booktitle = {Artificial Intelligence in Medicine - 19th International Conference
on Artificial Intelligence in Medicine, AIME 2021, Virtual Event,
June 15-18, 2021, Proceedings},
volume = {12721},
pages = {408--417},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kacupaj, Endri; Plepi, Joan; Singh, Kuldeep; Thakkar, Harsh; Lehmann, Jens; Maleshkova, Maria
Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks Inproceedings
In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, EACL 2021, Online, April 19 - 23, 2021, pp. 850–862, Association for Computational Linguistics, 2021.
@inproceedings{DBLP:conf/eacl/KacupajPSTLM21,
title = {Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks},
author = {Endri Kacupaj and
Joan Plepi and
Kuldeep Singh and
Harsh Thakkar and
Jens Lehmann and
Maria Maleshkova},
url = {https://www.aclweb.org/anthology/2021.eacl-main.72/},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the 16th Conference of the European Chapter of the
Association for Computational Linguistics: Main Volume, EACL 2021,
Online, April 19 - 23, 2021},
pages = {850--862},
publisher = {Association for Computational Linguistics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ravi, Manoj Prabhakar Kannan; Singh, Kuldeep; Mulang, Isaiah Onando; Shekarpour, Saeedeh; Hoffart, Johannes; Lehmann, Jens
CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata Inproceedings
In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, EACL 2021, Online, April 19 - 23, 2021, pp. 504–514, Association for Computational Linguistics, 2021.
@inproceedings{DBLP:conf/eacl/RaviSMSHL21,
title = {CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata},
author = {Manoj Prabhakar Kannan Ravi and
Kuldeep Singh and
Isaiah Onando Mulang and
Saeedeh Shekarpour and
Johannes Hoffart and
Jens Lehmann},
url = {https://www.aclweb.org/anthology/2021.eacl-main.40/},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the 16th Conference of the European Chapter of the
Association for Computational Linguistics: Main Volume, EACL 2021,
Online, April 19 - 23, 2021},
pages = {504--514},
publisher = {Association for Computational Linguistics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Chaudhuri, Debanjan; Rony, Md. Rashad Al Hasan; Lehmann, Jens
Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers Inproceedings
In: The Semantic Web - 18th International Conference, ESWC 2021, Virtual Event, June 6-10, 2021, Proceedings, pp. 323–339, Springer, 2021.
@inproceedings{DBLP:conf/esws/ChaudhuriR021,
title = {Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers},
author = {Debanjan Chaudhuri and
Md. Rashad Al Hasan Rony and
Jens Lehmann},
url = {https://doi.org/10.1007/978-3-030-77385-4_19},
doi = {10.1007/978-3-030-77385-4_19},
year = {2021},
date = {2021-01-01},
booktitle = {The Semantic Web - 18th International Conference, ESWC 2021, Virtual
Event, June 6-10, 2021, Proceedings},
volume = {12731},
pages = {323--339},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kacupaj, Endri; Banerjee, Barshana; Singh, Kuldeep; Lehmann, Jens
ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation Inproceedings
In: The Semantic Web - 18th International Conference, ESWC 2021, Virtual Event, June 6-10, 2021, Proceedings, pp. 598–613, Springer, 2021.
@inproceedings{DBLP:conf/esws/KacupajB0L21,
title = {ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation},
author = {Endri Kacupaj and
Barshana Banerjee and
Kuldeep Singh and
Jens Lehmann},
url = {https://doi.org/10.1007/978-3-030-77385-4_36},
doi = {10.1007/978-3-030-77385-4_36},
year = {2021},
date = {2021-01-01},
booktitle = {The Semantic Web - 18th International Conference, ESWC 2021, Virtual
Event, June 6-10, 2021, Proceedings},
volume = {12731},
pages = {598--613},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Plepi, Joan; Kacupaj, Endri; Singh, Kuldeep; Thakkar, Harsh; Lehmann, Jens
Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs Inproceedings
In: The Semantic Web - 18th International Conference, ESWC 2021, Virtual Event, June 6-10, 2021, Proceedings, pp. 356–371, Springer, 2021.
@inproceedings{DBLP:conf/esws/PlepiK0T021,
title = {Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs},
author = {Joan Plepi and
Endri Kacupaj and
Kuldeep Singh and
Harsh Thakkar and
Jens Lehmann},
url = {https://doi.org/10.1007/978-3-030-77385-4_21},
doi = {10.1007/978-3-030-77385-4_21},
year = {2021},
date = {2021-01-01},
booktitle = {The Semantic Web - 18th International Conference, ESWC 2021, Virtual
Event, June 6-10, 2021, Proceedings},
volume = {12731},
pages = {356--371},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Tavakoli, MohammadReza; Elias, Mirette; Kismihók, Gábor; Auer, Sören
Metadata Analysis of Open Educational Resources Inproceedings
In: LAKtextquotesingle 21: 11th International Learning Analytics and Knowledge Conference, Irvine, CA, USA, April 12-16, 2021, pp. 626–631, ACM, 2021.
@inproceedings{DBLP:conf/lak/TavakoliEKA21,
title = {Metadata Analysis of Open Educational Resources},
author = {MohammadReza Tavakoli and
Mirette Elias and
Gábor Kismihók and
Sören Auer},
url = {https://doi.org/10.1145/3448139.3448208},
doi = {10.1145/3448139.3448208},
year = {2021},
date = {2021-01-01},
booktitle = {LAKtextquotesingle 21: 11th International Learning Analytics and Knowledge Conference,
Irvine, CA, USA, April 12-16, 2021},
pages = {626--631},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Xu, Chengjin; Chen, Yung-Yu; Nayyeri, Mojtaba; Lehmann, Jens
Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings Inproceedings
In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021, pp. 2569–2578, Association for Computational Linguistics, 2021.
@inproceedings{DBLP:conf/naacl/XuCNL21,
title = {Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings},
author = {Chengjin Xu and
Yung-Yu Chen and
Mojtaba Nayyeri and
Jens Lehmann},
url = {https://www.aclweb.org/anthology/2021.naacl-main.202/},
year = {2021},
date = {2021-01-01},
booktitle = {Proceedings of the 2021 Conference of the North American Chapter of
the Association for Computational Linguistics: Human Language Technologies,
NAACL-HLT 2021, Online, June 6-11, 2021},
pages = {2569--2578},
publisher = {Association for Computational Linguistics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nayyeri, Mojtaba; Xu, Chengjin; Yaghoobzadeh, Yadollah; Vahdati, Sahar; Alam, Mirza Mohtashim; Yazdi, Hamed Shariat; Lehmann, Jens
Loss-Aware Pattern Inference: A Correction on the Wrongly Claimed Limitations of Embedding Models Inproceedings
In: Advances in Knowledge Discovery and Data Mining - 25th Pacific-Asia Conference, PAKDD 2021, Virtual Event, May 11-14, 2021, Proceedings, Part III, pp. 77–89, Springer, 2021.
@inproceedings{DBLP:conf/pakdd/NayyeriXYVAY021,
title = {Loss-Aware Pattern Inference: A Correction on the Wrongly Claimed
Limitations of Embedding Models},
author = {Mojtaba Nayyeri and
Chengjin Xu and
Yadollah Yaghoobzadeh and
Sahar Vahdati and
Mirza Mohtashim Alam and
Hamed Shariat Yazdi and
Jens Lehmann},
url = {https://doi.org/10.1007/978-3-030-75768-7_7},
doi = {10.1007/978-3-030-75768-7_7},
year = {2021},
date = {2021-01-01},
booktitle = {Advances in Knowledge Discovery and Data Mining - 25th Pacific-Asia
Conference, PAKDD 2021, Virtual Event, May 11-14, 2021, Proceedings,
Part III},
volume = {12714},
pages = {77--89},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Athreya, Ram G.; Bansal, Srividya; Ngomo, Axel-Cyrille Ngonga; Usbeck, Ricardo
Template-based Question Answering using Recursive Neural Networks Inproceedings
In: 15th IEEE International Conference on Semantic Computing, ICSC 2021, Laguna Hills, CA, USA, January 27-29, 2021, pp. 195–198, IEEE, 2021.
@inproceedings{DBLP:conf/semco/AthreyaBNU21,
title = {Template-based Question Answering using Recursive Neural Networks},
author = {Ram G. Athreya and
Srividya Bansal and
Axel-Cyrille Ngonga Ngomo and
Ricardo Usbeck},
url = {https://doi.org/10.1109/ICSC50631.2021.00041},
doi = {10.1109/ICSC50631.2021.00041},
year = {2021},
date = {2021-01-01},
booktitle = {15th IEEE International Conference on Semantic Computing, ICSC
2021, Laguna Hills, CA, USA, January 27-29, 2021},
pages = {195--198},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Elahi, Mehdi; Moghaddam, Farshad Bakhshandegan; Hosseini, Reza; Rimaz, Mohammad Hossein; Ioini, Nabil El; Tkalcic, Marko; Trattner, Christoph; Tillo, Tammam
Recommending Videos in Cold Start With Automatic Visual Tags Inproceedings
In: Adjunct Publication of the 29th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2021, Utrecht, The Netherlands, June 21-25, 2021, pp. 54–60, ACM, 2021.
@inproceedings{DBLP:conf/um/ElahiMHRITTT21,
title = {Recommending Videos in Cold Start With Automatic Visual Tags},
author = {Mehdi Elahi and
Farshad Bakhshandegan Moghaddam and
Reza Hosseini and
Mohammad Hossein Rimaz and
Nabil El Ioini and
Marko Tkalcic and
Christoph Trattner and
Tammam Tillo},
url = {https://doi.org/10.1145/3450614.3461687},
doi = {10.1145/3450614.3461687},
year = {2021},
date = {2021-01-01},
booktitle = {Adjunct Publication of the 29th ACM Conference on User Modeling,
Adaptation and Personalization, UMAP 2021, Utrecht, The Netherlands,
June 21-25, 2021},
pages = {54--60},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bastos, Anson; Nadgeri, Abhishek; Singh, Kuldeep; Mulang, Isaiah Onando; Shekarpour, Saeedeh; Hoffart, Johannes; Kaul, Manohar
RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network Inproceedings
In: WWW textquotesingle 21: The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021, pp. 1673–1685, ACM / IW3C2, 2021.
@inproceedings{DBLP:conf/www/BastosN0MSHK21,
title = {RECON: Relation Extraction using Knowledge Graph Context in a Graph
Neural Network},
author = {Anson Bastos and
Abhishek Nadgeri and
Kuldeep Singh and
Isaiah Onando Mulang and
Saeedeh Shekarpour and
Johannes Hoffart and
Manohar Kaul},
url = {https://doi.org/10.1145/3442381.3449917},
doi = {10.1145/3442381.3449917},
year = {2021},
date = {2021-01-01},
booktitle = {WWW textquotesingle 21: The Web Conference 2021, Virtual Event / Ljubljana, Slovenia,
April 19-23, 2021},
pages = {1673--1685},
publisher = {ACM / IW3C2},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ali, Mohamed Hassan Mohamed; Fathalla, Said; Kholief, Mohamed; Hassan, Yasser Fouad
Learning Non-Taxonomic Relations of Ontologies: A Systematic Review Journal Article
In: Int. J. Semantic Web Inf. Syst., vol. 17, no. 1, pp. 97–122, 2021.
@article{DBLP:journals/ijswis/AliFKH21,
title = {Learning Non-Taxonomic Relations of Ontologies: A Systematic Review},
author = {Mohamed Hassan Mohamed Ali and
Said Fathalla and
Mohamed Kholief and
Yasser Fouad Hassan},
url = {https://doi.org/10.4018/IJSWIS.2021010105},
doi = {10.4018/IJSWIS.2021010105},
year = {2021},
date = {2021-01-01},
journal = {Int. J. Semantic Web Inf. Syst.},
volume = {17},
number = {1},
pages = {97--122},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Adamczak, Jens; Deldjoo, Yashar; Moghaddam, Farshad Bakhshandegan; Knees, Peter; Leyson, Gerard Paul; Monreal, Philipp
Session-based Hotel Recommendations Dataset: As part of the ACM Recommender System Challenge 2019 Journal Article
In: ACM Trans. Intell. Syst. Technol., vol. 12, no. 1, pp. 1:1–1:20, 2021.
@article{DBLP:journals/tist/AdamczakDMKLM21,
title = {Session-based Hotel Recommendations Dataset: As part of the ACM Recommender System Challenge 2019},
author = {Jens Adamczak and
Yashar Deldjoo and
Farshad Bakhshandegan Moghaddam and
Peter Knees and
Gerard Paul Leyson and
Philipp Monreal},
url = {https://doi.org/10.1145/3412379},
doi = {10.1145/3412379},
year = {2021},
date = {2021-01-01},
journal = {ACM Trans. Intell. Syst. Technol.},
volume = {12},
number = {1},
pages = {1:1--1:20},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Galetzka, Fabian; Rose, Jewgeni; Schlangen, David; Lehmann, Jens
Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer Inproceedings
In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pp. 7028–7041, Association for Computational Linguistics, 2021.
@inproceedings{DBLP:conf/acl/GaletzkaRS020,
title = {Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer},
author = {Fabian Galetzka and
Jewgeni Rose and
David Schlangen and
Jens Lehmann},
url = {https://doi.org/10.18653/v1/2021.acl-long.546},
doi = {10.18653/v1/2021.acl-long.546},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational
Linguistics and the 11th International Joint Conference on Natural
Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual
Event, August 1-6, 2021},
pages = {7028--7041},
publisher = {Association for Computational Linguistics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nadgeri, Abhishek; Bastos, Anson; Singh, Kuldeep; Mulang, Isaiah Onando; Hoffart, Johannes; Shekarpour, Saeedeh; Saraswat, Vijay
KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction Inproceedings
In: Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event, August 1-6, 2021, pp. 535–548, Association for Computational Linguistics, 2021.
@inproceedings{DBLP:conf/acl/NadgeriBSMHSS21,
title = {KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction},
author = {Abhishek Nadgeri and
Anson Bastos and
Kuldeep Singh and
Isaiah Onando Mulang and
Johannes Hoffart and
Saeedeh Shekarpour and
Vijay Saraswat},
url = {https://doi.org/10.18653/v1/2021.findings-acl.48},
doi = {10.18653/v1/2021.findings-acl.48},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Findings of the Association for Computational Linguistics: ACL/IJCNLP
2021, Online Event, August 1-6, 2021},
volume = {ACL/IJCNLP 2021},
pages = {535--548},
publisher = {Association for Computational Linguistics},
series = {Findings of ACL},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Wilhelm, Nico; Collarana, Diego; Lehmann, Jens
A Virtual Knowledge Graph for Enabling Defect Traceability and Customer Service Analytics Inproceedings
In: The Semantic Web: ESWC 2021 Satellite Events - Virtual Event, June 6-10, 2021, Revised Selected Papers, pp. 245–248, Springer, 2021.
@inproceedings{DBLP:conf/esws/WilhelmCL21,
title = {A Virtual Knowledge Graph for Enabling Defect Traceability and Customer Service Analytics},
author = {Nico Wilhelm and
Diego Collarana and
Jens Lehmann},
url = {https://doi.org/10.1007/978-3-030-80418-3_36},
doi = {10.1007/978-3-030-80418-3_36},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {The Semantic Web: ESWC 2021 Satellite Events - Virtual Event, June
6-10, 2021, Revised Selected Papers},
volume = {12739},
pages = {245--248},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sadeghi, Afshin; Shahini, Xhulia; Schmitz, Martin; Lehmann, Jens
BenchEmbedd: A FAIR Benchmarking tool for Knowledge Graph Embeddings Inproceedings
In: Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins co-located with Semantics 2021, Amsterdam and Online, September 6-9, 2021, CEUR-WS.org, 2021.
@inproceedings{DBLP:conf/i-semantics/SadeghiSS021,
title = {BenchEmbedd: A FAIR Benchmarking tool for Knowledge Graph Embeddings},
author = {Afshin Sadeghi and
Xhulia Shahini and
Martin Schmitz and
Jens Lehmann},
url = {http://ceur-ws.org/Vol-2941/paper14.pdf},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Joint Proceedings of the Semantics co-located events: Poster&Demo
track and Workshop on Ontology-Driven Conceptual Modelling of Digital
Twins co-located with Semantics 2021, Amsterdam and Online, September
6-9, 2021},
volume = {2941},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kacupaj, Endri; Premnadh, Shyamnath; Singh, Kuldeep; Lehmann, Jens; Maleshkova, Maria
VOGUE: Answer Verbalization Through Multi-Task Learning Inproceedings
In: Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2021, Bilbao, Spain, September 13-17, 2021, Proceedings, Part III, pp. 563–579, Springer, 2021.
@inproceedings{DBLP:conf/pkdd/KacupajPSLM21,
title = {VOGUE: Answer Verbalization Through Multi-Task Learning},
author = {Endri Kacupaj and
Shyamnath Premnadh and
Kuldeep Singh and
Jens Lehmann and
Maria Maleshkova},
url = {https://doi.org/10.1007/978-3-030-86523-8_34},
doi = {10.1007/978-3-030-86523-8_34},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Machine Learning and Knowledge Discovery in Databases. Research Track
- European Conference, ECML PKDD 2021, Bilbao, Spain, September
13-17, 2021, Proceedings, Part III},
volume = {12977},
pages = {563--579},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sadeghi, Afshin; Collarana, Diego; Graux, Damien; Lehmann, Jens
Embedding Knowledge Graphs Attentive to Positional and Centrality Qualities Inproceedings
In: Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2021, Bilbao, Spain, September 13-17, 2021, Proceedings, Part II, pp. 548–564, Springer, 2021.
@inproceedings{DBLP:conf/pkdd/SadeghiCGL21,
title = {Embedding Knowledge Graphs Attentive to Positional and Centrality
Qualities},
author = {Afshin Sadeghi and
Diego Collarana and
Damien Graux and
Jens Lehmann},
url = {https://doi.org/10.1007/978-3-030-86520-7_34},
doi = {10.1007/978-3-030-86520-7_34},
year = {2021},
date = {2021-01-01},
booktitle = {Machine Learning and Knowledge Discovery in Databases. Research Track
- European Conference, ECML PKDD 2021, Bilbao, Spain, September
13-17, 2021, Proceedings, Part II},
volume = {12976},
pages = {548--564},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ali, Mehdi; Berrendorf, Max; Galkin, Mikhail; Thost, Veronika; Ma, Tengfei; Tresp, Volker; Lehmann, Jens
Improving Inductive Link Prediction Using Hyper-relational Facts Inproceedings
In: The Semantic Web - ISWC 2021 - 20th International Semantic Web Conference, ISWC 2021, Virtual Event, October 24-28, 2021, Proceedings, pp. 74–92, Springer, 2021.
@inproceedings{DBLP:conf/semweb/AliB0TMT021,
title = {Improving Inductive Link Prediction Using Hyper-relational Facts},
author = {Mehdi Ali and
Max Berrendorf and
Mikhail Galkin and
Veronika Thost and
Tengfei Ma and
Volker Tresp and
Jens Lehmann},
url = {https://doi.org/10.1007/978-3-030-88361-4_5},
doi = {10.1007/978-3-030-88361-4_5},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {The Semantic Web - ISWC 2021 - 20th International Semantic Web Conference,
ISWC 2021, Virtual Event, October 24-28, 2021, Proceedings},
volume = {12922},
pages = {74--92},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Avogadro, Roberto; Cremaschi, Marco; Jiménez-Ruiz, Ernesto; Rula, Anisa
A Framework for Quality Assessment of Semantic Annotations of Tabular Data Inproceedings
In: The Semantic Web - ISWC 2021 - 20th International Semantic Web Conference, ISWC 2021, Virtual Event, October 24-28, 2021, Proceedings, pp. 528–545, Springer, 2021.
@inproceedings{DBLP:conf/semweb/AvogadroCJR21,
title = {A Framework for Quality Assessment of Semantic Annotations of Tabular Data},
author = {Roberto Avogadro and
Marco Cremaschi and
Ernesto Jiménez-Ruiz and
Anisa Rula},
url = {https://doi.org/10.1007/978-3-030-88361-4_31},
doi = {10.1007/978-3-030-88361-4_31},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {The Semantic Web - ISWC 2021 - 20th International Semantic Web Conference,
ISWC 2021, Virtual Event, October 24-28, 2021, Proceedings},
volume = {12922},
pages = {528--545},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Tahmasebzadeh, Golsa; Kacupaj, Endri; Müller-Budack, Eric; Hakimov, Sherzod; Lehmann, Jens; Ewerth, Ralph
GeoWINE: Geolocation based Wiki, Image, News and Event Retrieval Inproceedings
In: SIGIR textquotesingle 21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, pp. 2565–2569, ACM, 2021.
@inproceedings{DBLP:conf/sigir/TahmasebzadehKM21,
title = {GeoWINE: Geolocation based Wiki, Image, News and Event Retrieval},
author = {Golsa Tahmasebzadeh and
Endri Kacupaj and
Eric Müller-Budack and
Sherzod Hakimov and
Jens Lehmann and
Ralph Ewerth},
url = {https://doi.org/10.1145/3404835.3462786},
doi = {10.1145/3404835.3462786},
year = {2021},
date = {2021-01-01},
booktitle = {SIGIR textquotesingle 21: The 44th International ACM SIGIR Conference on Research
and Development in Information Retrieval, Virtual Event, Canada, July
11-15, 2021},
pages = {2565--2569},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nayyeri, Mojtaba; Cil, Gökce Müge; Vahdati, Sahar; Osborne, Francesco; Kravchenko, Andrey; Angioni, Simone; Salatino, Angelo A.; Recupero, Diego Reforgiato; Motta, Enrico; Lehmann, Jens
Link Prediction of Weighted Ŧriples for Knowledge Graph Completion Within the Scholarly Đomain Journal Article
In: IEEE Access, vol. 9, pp. 116002–116014, 2021.
@article{DBLP:journals/access/NayyeriCVOKASRM21,
title = {Link Prediction of Weighted Ŧriples for Knowledge Graph Completion
Within the Scholarly Đomain},
author = {Mojtaba Nayyeri and
Gökce Müge Cil and
Sahar Vahdati and
Francesco Osborne and
Andrey Kravchenko and
Simone Angioni and
Angelo A. Salatino and
Diego Reforgiato Recupero and
Enrico Motta and
Jens Lehmann},
url = {https://doi.org/10.1109/ACCESS.2021.3105183},
doi = {10.1109/ACCESS.2021.3105183},
year = {2021},
date = {2021-01-01},
journal = {IEEE Access},
volume = {9},
pages = {116002--116014},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Vollmers, Daniel; Jalota, Rricha; Moussallem, Diego; Topiwala, Hardik; Ngomo, Axel-Cyrille Ngonga; Usbeck, Ricardo
Knowledge Graph Question Answering using Graph-Pattern Isomorphism Journal Article
In: CoRR, vol. abs/2103.06752, 2021.
@article{DBLP:journals/corr/abs-2103-06752,
title = {Knowledge Graph Question Answering using Graph-Pattern Isomorphism},
author = {Daniel Vollmers and
Rricha Jalota and
Diego Moussallem and
Hardik Topiwala and
Axel-Cyrille Ngonga Ngomo and
Ricardo Usbeck},
url = {https://arxiv.org/abs/2103.06752},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2103.06752},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Xu, Chengjin; Nayyeri, Mojtaba; Vahdati, Sahar; Lehmann, Jens
Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings Journal Article
In: CoRR, vol. abs/2104.05003, 2021.
@article{DBLP:journals/corr/abs-2104-05003,
title = {Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings},
author = {Chengjin Xu and
Mojtaba Nayyeri and
Sahar Vahdati and
Jens Lehmann},
url = {https://arxiv.org/abs/2104.05003},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2104.05003},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Biswas, Debanjali; Dubey, Mohnish; Rony, Md. Rashad Al Hasan; Lehmann, Jens
VANiLLa : Verbalized Answers in Natural Language at Large Scale Journal Article
In: CoRR, vol. abs/2105.11407, 2021.
@article{DBLP:journals/corr/abs-2105-11407,
title = {VANiLLa : Verbalized Answers in Natural Language at Large Scale},
author = {Debanjali Biswas and
Mohnish Dubey and
Md. Rashad Al Hasan Rony and
Jens Lehmann},
url = {https://arxiv.org/abs/2105.11407},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.11407},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wenige, Lisa; Stadler, Claus; Martin, Michael; Figura, Richard; Sauter, Robert; Frank, Christopher W.
Open Data and the Status Quo - A Fine-Grained Evaluation Framework for Open Data Quality and an Analysis of Open Data portals in Germany Journal Article
In: CoRR, vol. abs/2106.09590, 2021.
@article{DBLP:journals/corr/abs-2106-09590,
title = {Open Data and the Status Quo - A Fine-Grained Evaluation Framework for Open Data Quality and an Analysis of Open Data portals in Germany},
author = {Lisa Wenige and
Claus Stadler and
Michael Martin and
Richard Figura and
Robert Sauter and
Christopher W. Frank},
url = {https://arxiv.org/abs/2106.09590},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2106.09590},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Bastos, Anson; Singh, Kuldeep; Nadgeri, Abhishek; Shekarpour, Saeedeh; Mulang, Isaiah Onando; Hoffart, Johannes
HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations Journal Article
In: CoRR, vol. abs/2108.05774, 2021.
@article{DBLP:journals/corr/abs-2108-05774,
title = {HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations},
author = {Anson Bastos and
Kuldeep Singh and
Abhishek Nadgeri and
Saeedeh Shekarpour and
Isaiah Onando Mulang and
Johannes Hoffart},
url = {https://arxiv.org/abs/2108.05774},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2108.05774},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Grubenmann, Tobias; Lehmann, Jens
Geolog: Scalable Logic Programming on Spatial Đata Journal Article
In: CoRR, vol. abs/2109.08295, 2021.
@article{DBLP:journals/corr/abs-2109-08295,
title = {Geolog: Scalable Logic Programming on Spatial Đata},
author = {Tobias Grubenmann and
Jens Lehmann},
url = {https://arxiv.org/abs/2109.08295},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2109.08295},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Hogan, Aidan; Blomqvist, Eva; Cochez, Michael; dtextquotesingle Amato, Claudia; de Melo, Gerard; Gutiérrez, Claudio; Kirrane, Sabrina; Gayo, José Emilio Labra; Navigli, Roberto; Neumaier, Sebastian; Ngomo, Axel-Cyrille Ngonga; Polleres, Axel; Rashid, Sabbir M.; Rula, Anisa; Schmelzeisen, Lukas; Sequeda, Juan F.; Staab, Steffen; Zimmermann, Antoine
Knowledge Graphs Journal Article
In: ACM Comput. Surv., vol. 54, no. 4, pp. 71:1–71:37, 2021.
@article{DBLP:journals/csur/HoganBCdMGKGNNN21,
title = {Knowledge Graphs},
author = {Aidan Hogan and
Eva Blomqvist and
Michael Cochez and
Claudia dtextquotesingle Amato and
Gerard de Melo and
Claudio Gutiérrez and
Sabrina Kirrane and
José Emilio Labra Gayo and
Roberto Navigli and
Sebastian Neumaier and
Axel-Cyrille Ngonga Ngomo and
Axel Polleres and
Sabbir M. Rashid and
Anisa Rula and
Lukas Schmelzeisen and
Juan F. Sequeda and
Steffen Staab and
Antoine Zimmermann},
url = {https://doi.org/10.1145/3447772},
doi = {10.1145/3447772},
year = {2021},
date = {2021-01-01},
journal = {ACM Comput. Surv.},
volume = {54},
number = {4},
pages = {71:1--71:37},
keywords = {},
pubstate = {published},
tppubtype = {article}
}