Dr. Kuldeep Singh

Innovation Manager – Automotive R&D
Cerence GmbH

Profiles: LinkedIn, Google Scholar, DBLP

kuldeep.singh1@cerence.com

Short CV

Dr. Kuldeep Singh is a associated researcher with SDA. He currently works in Cerence GmbH. He is part of the Innovation management team and driving innovation in conversational AI-related products for tier-1 OEMs. He is responsible for the success of a few next-gen innovative conversational AI products of Cerence.

Research Interests

Question Answering
Knowledge Graphs Completion
Natural Language Processing

Projects

WDAqua

Publication

2021

Jaradeh, Mohamad Yaser; Singh, Kuldeep; Stocker, Markus; Both, Andreas; Auer, Sören

Better Call the Plumber: Orchestrating Dynamic Information Extraction Pipelines Inproceedings

In: Web Engineering - 21st International Conference, ICWE 2021, Biarritz, France, May 18-21, 2021, Proceedings, pp. 240–254, Springer, 2021.

Jaradeh, Mohamad Yaser; Singh, Kuldeep; Stocker, Markus; Auer, Sören

Plumber: A Modular Framework to Create Information Extraction Pipelines Inproceedings

In: Companion of The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021, pp. 678–679, ACM / IW3C2, 2021.

2020

Mulang, Isaiah Onando; Singh, Kuldeep; Vyas, Akhilesh; Shekarpour, Saeedeh; Vidal, Maria-Esther; Auer, Sören

Encoding Knowledge Graph Entity Aliases in Attentive Neural Network for Wikidata Entity Linking Inproceedings

In: Web Information Systems Engineering - WISE 2020 - 21st International Conference, Amsterdam, The Netherlands, October 20-24, 2020, Proceedings, Part I, pp. 328–342, Springer, 2020.

2019

Sakor, Ahmad; Mulang, Isaiah Onando; Singh, Kuldeep; Shekarpour, Saeedeh; Vidal, Maria-Esther; Lehmann, Jens; Auer, Sören

Old is Gold: Linguistic Driven Approach for Entity and Relation Linking of Short Text Inproceedings

In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pp. 2336–2346, Association for Computational Linguistics, 2019.

Mehmood, Qaiser; Nadgeri, Abhishek; Saleem, Muhammad; Singh, Kuldeep; Ngomo, Axel-Cyrille Ngonga; Lehmann, Jens

Microbenchmarks for Question Answering Systems Using QaldGen Inproceedings

In: Proceedings of the ISWC 2019 Satellite Tracks (Posters & Demonstrations, Industry, and Outrageous Ideas) co-located with 18th International Semantic Web Conference (ISWC 2019), Auckland, New Zealand, October 26-30, 2019, pp. 261–264, CEUR-WS.org, 2019.

Singh, Kuldeep; Saleem, Muhammad; Nadgeri, Abhishek; Conrads, Felix; Pan, Jeff Z.; Ngomo, Axel-Cyrille Ngonga; Lehmann, Jens

QaldGen: Towards Microbenchmarking of Question Answering Systems over Knowledge Graphs Inproceedings

In: The Semantic Web - ISWC 2019 - 18th International Semantic Web Conference, Auckland, New Zealand, October 26-30, 2019, Proceedings, Part II, pp. 277–292, Springer, 2019.

Singh, Kuldeep

Towards Dynamic Composition of Question Answering Pipelines PhD Thesis

University of Bonn, Germany, 2019.

Abstract | Links | BibTeX

@phdthesis{DBLP:phd/dnb/Singh19,

title = {Towards Dynamic Composition of Question Answering Pipelines},

author = {Kuldeep Singh},

url = {https://d-nb.info/1188730762/34},

year = {2019},

date = {2019-01-01},

school = {University of Bonn, Germany},

abstract = {Question answering (QA) over knowledge graphs has gained significant momentum over the past five years due to the increasing availability of large knowledge graphs and the rising importance of question answering for user interaction. DBpedia has been the most prominently used knowledge graph in this setting. QA systems implement a pipeline connecting a sequence of QA components for translating an input question into its corresponding formal query (e.g. SPARQL); this query will be executed over a knowledge graph in order to produce the answer of the question. Recent empirical studies have revealed that albeit overall effective, the performance of QA systems and QA components depends heavily on the features of input questions, and not even the combination of the best performing QA systems or individual QA components retrieves complete and correct answers. Furthermore, these QA systems cannot be easily reused, extended, and results cannot be easily reproduced since the systems are mostly implemented in a monolithic fashion, lack standardised interfaces, and are often not open source or available as Web services. All these drawbacks of the state of the art that prevents many of these approaches to be employed in real-world applications. In this thesis, we tackle the problem of QA over the knowledge graph and propose a generic approach to promote reusability and build question answering systems in a collaborative effort. Firstly, we define qa vocabulary and Qanary methodology to develop an abstraction level on existing QA systems and components. Qanary relies on qa vocabulary to establish guidelines for semantically describing the knowledge exchange between the components of a QA system. We implement a component-based modular framework called "Qanary Ecosystem" utilising the Qanary methodology to integrate several heterogeneous QA components in a single platform. We further present Qaestro framework that provides an approach to semantically describing question answering components and effectively enumerates QA pipelines based on a QA developer requirements. Qaestro provides all valid combinations of available QA components respecting the input-output requirement of each component to build QA pipelines. Finally, we address the scalability of QA components within a framework and propose a novel approach that chooses the best component per task to automatically build QA pipeline for each input question. We implement this model within FRANKENSTEIN, a framework able to select QA components and compose pipelines. FRANKENSTEIN extends Qanary ecosystem and utilises qa vocabulary for data exchange. It has 29 independent QA components implementing five QA tasks resulting in 360 unique QA pipelines. Each approach proposed in this thesis (Qanary methodology, Qaestro, and FRANKENSTEIN) is supported by extensive evaluation to demonstrate their effectiveness. Our contributions target a broader research agenda of offering the QA community an efficient way of applying their research to a research field which is driven by many different fields, consequently requiring a collaborative approach to achieve significant progress in the domain of question answering.},

keywords = {},

pubstate = {published},

tppubtype = {phdthesis}

}

Question answering (QA) over knowledge graphs has gained significant momentum over the past five years due to the increasing availability of large knowledge graphs and the rising importance of question answering for user interaction. DBpedia has been the most prominently used knowledge graph in this setting. QA systems implement a pipeline connecting a sequence of QA components for translating an input question into its corresponding formal query (e.g. SPARQL); this query will be executed over a knowledge graph in order to produce the answer of the question. Recent empirical studies have revealed that albeit overall effective, the performance of QA systems and QA components depends heavily on the features of input questions, and not even the combination of the best performing QA systems or individual QA components retrieves complete and correct answers. Furthermore, these QA systems cannot be easily reused, extended, and results cannot be easily reproduced since the systems are mostly implemented in a monolithic fashion, lack standardised interfaces, and are often not open source or available as Web services. All these drawbacks of the state of the art that prevents many of these approaches to be employed in real-world applications. In this thesis, we tackle the problem of QA over the knowledge graph and propose a generic approach to promote reusability and build question answering systems in a collaborative effort. Firstly, we define qa vocabulary and Qanary methodology to develop an abstraction level on existing QA systems and components. Qanary relies on qa vocabulary to establish guidelines for semantically describing the knowledge exchange between the components of a QA system. We implement a component-based modular framework called "Qanary Ecosystem" utilising the Qanary methodology to integrate several heterogeneous QA components in a single platform. We further present Qaestro framework that provides an approach to semantically describing question answering components and effectively enumerates QA pipelines based on a QA developer requirements. Qaestro provides all valid combinations of available QA components respecting the input-output requirement of each component to build QA pipelines. Finally, we address the scalability of QA components within a framework and propose a novel approach that chooses the best component per task to automatically build QA pipeline for each input question. We implement this model within FRANKENSTEIN, a framework able to select QA components and compose pipelines. FRANKENSTEIN extends Qanary ecosystem and utilises qa vocabulary for data exchange. It has 29 independent QA components implementing five QA tasks resulting in 360 unique QA pipelines. Each approach proposed in this thesis (Qanary methodology, Qaestro, and FRANKENSTEIN) is supported by extensive evaluation to demonstrate their effectiveness. Our contributions target a broader research agenda of offering the QA community an efficient way of applying their research to a research field which is driven by many different fields, consequently requiring a collaborative approach to achieve significant progress in the domain of question answering.

Sakor, Ahmad; Singh, Kuldeep; Vidal, Maria-Esther

FALCON: An Entity and Relation Linking Framework over DBpedia Inproceedings

In: Proceedings of the ISWC 2019 Satellite Tracks (Posters & Demonstrations, Industry, and Outrageous Ideas) co-located with 18th International Semantic Web Conference (ISWC 2019), Auckland, New Zealand, October 26-30, 2019, pp. 265–268, CEUR-WS.org, 2019.

2018

Singh, Kuldeep; Lytra, Ioanna; Radhakrishna, Arun Sethupat; Vyas, Akhilesh; Vidal, Maria-Esther

Dynamic Composition of Question Answering Pipelines with FRANKENSTEIN Inproceedings

In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08-12, 2018, pp. 1313–1316, ACM, 2018.

Singh, Kuldeep; Radhakrishna, Arun Sethupat; Both, Andreas; Shekarpour, Saeedeh; Lytra, Ioanna; Usbeck, Ricardo; Vyas, Akhilesh; Khikmatullaev, Akmal; Punjani, Dharmen; Lange, Christoph; Vidal, Maria-Esther; Lehmann, Jens; Auer, Sören

Why Reinvent the Wheel: Let's Build Question Answering Systems Together Inproceedings

In: Proceedings of the 2018 World Wide Web Conference on World Wide Web, WWW 2018, Lyon, France, April 23-27, 2018, pp. 1247–1256, ACM, 2018.

Singh, Kuldeep; Lytra, Ioanna; Radhakrishna, Arun Sethupat; Shekarpour, Saeedeh; Vidal, Maria-Esther; Lehmann, Jens

No One is Perfect: Analysing the Performance of Question Answering Components over the DBpedia Knowledge Graph Journal Article

In: CoRR, abs/1809.10044 , 2018.

Singh, Kuldeep; Both, Andreas; Radhakrishna, Arun Sethupat; Shekarpour, Saeedeh

Frankenstein: A Platform Enabling Reuse of Question Answering Components Inproceedings

In: The Semantic Web - 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3-7, 2018, Proceedings, pp. 624–638, Springer, 2018.

2017

Singh, Kuldeep; Lytra, Ioanna; Vidal, Maria-Esther; Punjani, Dharmen; Thakkar, Harsh; Lange, Christoph; Auer, Sören

QAestro - Semantic-Based Composition of Question Answering Pipelines Inproceedings

In: Database and Expert Systems Applications - 28th International Conference, DEXA 2017, Lyon, France, August 28-31, 2017, Proceedings, Part I, pp. 19–34, Springer, 2017.

Mulang, Isaiah Onando; Singh, Kuldeep; Orlandi, Fabrizio

Matching Natural Language Relations to Knowledge Graph Properties for Question Answering Inproceedings

In: Proceedings of the 13th International Conference on Semantic Systems, SEMANTICS 2017, Amsterdam, The Netherlands, September 11-14, 2017, pp. 89–96, ACM, 2017.

Both, Andreas; Singh, Kuldeep; Diefenbach, Dennis; Lytra, Ioanna

Rapid Engineering of QA Systems Using the Light-Weight Qanary Architecture Inproceedings

In: Web Engineering - 17th International Conference, ICWE 2017, Rome, Italy, June 5-8, 2017, Proceedings, pp. 544–548, Springer, 2017.

Diefenbach, Dennis; Singh, Kuldeep; Both, Andreas; Cherix, Didier; Lange, Christoph; Auer, Sören

The Qanary Ecosystem: Getting New Insights by Composing Question Answering Pipelines Inproceedings

In: Web Engineering - 17th International Conference, ICWE 2017, Rome, Italy, June 5-8, 2017, Proceedings, pp. 171–189, Springer, 2017.

Singh, Kuldeep; Mulang, Isaiah Onando; Lytra, Ioanna; Jaradeh, Mohamad Yaser; Sakor, Ahmad; Vidal, Maria-Esther; Lange, Christoph; Auer, Sören

Capturing Knowledge in Semantically-typed Relational Patterns to Enhance Relation Linking Inproceedings

In: Proceedings of the Knowledge Capture Conference, K-CAP 2017, Austin, TX, USA, December 4-6, 2017, pp. 31:1–31:8, ACM, 2017.

Singh, Kuldeep; Lytra, Ioanna; Aditya, Kunwar Abhinav; Vidal, Maria-Esther

QAestro Framework - Semantic Composition of QA Pipelines Inproceedings

In: Proceedings of the ISWC 2017 Posters & Demonstrations and Industry Tracks co-located with 16th International Semantic Web Conference (ISWC 2017), Vienna, Austria, October 23rd - to - 25th, 2017, CEUR-WS.org, 2017.

2016

kmueller stadler singh hellmann,

Towards Sustainable view-based Extract-Transform-Load (ETL) Fusion of Open Data Inproceedings

In: Proceedings of the Workshop on 3rd Workshop on Linked Data Quality co-located with the European Semantic Web Conference 2016 (ESWC 2016), 2016.

Abstract | Links | BibTeX

Both, Andreas; Diefenbach, Dennis; Singh, Kuldeep; Shekarpour, Saeedeh; Cherix, Didier; Lange, Christoph

Qanary - A Methodology for Vocabulary-Driven Open Question Answering Systems Inproceedings

In: The Semantic Web. Latest Advances and New Domains - 13th International Conference, ESWC 2016, Heraklion, Crete, Greece, May 29 - June 2, 2016, Proceedings, pp. 625–641, Springer, 2016.

Singh, Kuldeep; Both, Andreas; Diefenbach, Dennis; Shekarpour, Saeedeh; Cherix, Didier; Lange, Christoph

Qanary - The Fast Track to Creating a Question Answering System with Linked Data Technology Inproceedings

In: The Semantic Web - ESWC 2016 Satellite Events, Heraklion, Crete, Greece, May 29 - June 2, 2016, Revised Selected Papers, pp. 183–188, 2016.

Shekarpour, Saeedeh; Endris, Kemele M.; Kumar, Ashwini Jaya; Lukovnikov, Denis; Singh, Kuldeep; Thakkar, Harsh; Lange, Christoph

Question Answering on Linked Data: Challenges and Future Directions Inproceedings

In: Proceedings of the 25th International Conference on World Wide Web, WWW 2016, Montreal, Canada, April 11-15, 2016, Companion Volume, pp. 693–698, ACM, 2016.

Singh, Kuldeep; Both, Andreas; Diefenbach, Dennis; Shekarpour, Saeedeh

Towards a Message-Driven Vocabulary for Promoting the Interoperability of Question Answering Systems Inproceedings

In: Tenth IEEE International Conference on Semantic Computing, ICSC 2016, Laguna Hills, CA, USA, February 4-6, 2016, pp. 386–389, IEEE Computer Society, 2016.

2013

Gupta, Anant; Singh, Kuldeep

Location based personalized restaurant recommendation system for mobile environments Inproceedings

In: International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013, Mysore, India, August 22-25, 2013, pp. 507–511, IEEE, 2013.