Papers accepted at AAAI / CompexQA & RecNLP Workshops
We are very pleased to announce that our group got two papers got accepted for presentation at the Thirty-First The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19) workshops (ComplexQA 2019 and RecNLP 2019), which will be held January 27 – February 1, 2019 at the Hilton Hawaiian Village, Honolulu, Hawaii, USA. The purpose of the Association for the Advancement of Artificial Intelligence (AAAI) conference series is to promote research in artificial intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers in AI and its affiliated disciplines. Reasoning for Complex Question Answering Workshop is a new series of workshops on the reasoning for complex question answering (QA). QA has become a crucial application problem in evaluating the progress of AI systems in the realm of natural language processing and understanding, and to measure the progress of machine intelligence in general. The computational linguistics communities (ACL, NAACL, EMNLP et al.) have devoted significant attention to the general problem of machine reading and question answering, as evidenced by the emergence of strong technical contributions and challenge datasets such as SQuAD. However, most of these advances have focused on “shallow” QA tasks that can be tackled very effectively by existing retrieval-based techniques. Instead of measuring the comprehension and understanding of the QA systems in question, these tasks test merely the capability of a technique to “attend” or focus attention on specific words and pieces of text. The main aim of this workshop is to bring together experts from the computational linguistics (CL) and AI communities to: (1) catalyze progress on the CQA problem, and create a vibrant test-bed of problems for various AI sub-fields; and (2) present a generalized task that can act as a harbinger of progress in AI. Recommender Systems Meet Natural Language Processing (RecNLP) is an interdisciplinary workshop covering the intersection between Recommender Systems (RecSys) and Natural Language Processing (NLP). The primary goal of RecNLP is to identify common ideas and techniques that are being developed in both disciplines, and to further explore the synergy between the two and to bring together researchers from both domains to encourage and facilitate future collaborations. Here is the pre-print of the accepted papers with their abstract:
- Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters by Denis Lukovnikov, Nilesh Chakraborty, Jens Lehmann and Asja Fischer
Abstract: Translating natural language to SQL queries for table-based question answering is a challenging problem and has received significant attention from the research community. In this work, we extend a pointer-generator network and investigate how query decoding order matters in semantic parsing for SQL. Even though our model is a straightforward extension of a general-purpose pointer-generator, it outperforms early work for WikiSQL and remains competitive to concurrently introduced, more complex models. Moreover, we provide a deeper investigation of the potential “order-matters” problem due to having multiple correct decoding paths, and investigate the use of REINFORCE as well as a non-deterministic oracle in this context.
- Metaresearch Recommendations using Knowledge Graph Embeddings by Veronika Henk, Sahar Vahdati, Mojataba Nayyeri, Mehdi Ali, Hamed Shariat Yazdi and Jens Lehmann
Abstract: Discovering relevant research collaborations is crucial for performing extraordinary research and promoting the careers of scholars. Therefore, building recommender systems capable of suggesting relevant collaboration opportunities is of huge interest. Most of the existing approaches for collaboration and co-author recommendation focus on semantic similarities using bibliographic metadata such as publication counts, and citation network analysis. These approaches neglect relevant and important metadata information such as author affiliation and conferences attended, affecting the quality of the recommendations. To overcome these drawbacks, we formulate the task of scholarly recommendation as a link prediction task based on knowledge graph embeddings. A knowledge graph containing scholarly metadata is created and enriched with textual descriptions. We tested the quality of the recommendations based on the TransE, TranH and DistMult models that consider only triples in the knowledge graph and DKRL which in addition incorporates natural language descriptions of entities during training.
Looking forward to seeing you at The AAAI-19.