First International Workshop on Hybrid Question Answering with Structured and Unstructured Knowledge
Part of WWW'18, April 23, 2018, Lyon, France
CFP can be downloaded from cfp-haq18.pdf.
- Title and abstract submission:
February 1, 2018 February 5, 2018 (Anywhere on Earth)
- Paper submission:
February 5, 2018 February 8, 2018
February 16, 2018
- Early-bird registrations deadline:
February 21, 2018 February 28, 2018
- Final version due:
March 4, 2018 (strong deadline)
- Workshop day: April 23, 2018
More and more knowledge is available electronically in a structured or unstructured form over the World Wide Web (WWW). Such knowledge has become a rich resource to answer our daily life questions and even scientific questions posed by domain experts. Accordingly, it becomes a necessity to develop tools that can (semi-)automatically answer questions based on the large amount of available data.
Such challenges have been targeted separately over the last years by different communities, including Query Answering in Semantic Web based on structured semantic data and Question Answering in Natural Language Processing based on unstructured textual data. While the former is powerful in representing complex questions and exploring background knowledge (e.g., large biomedical ontologies), it is often difficult to master and cannot be used without a specialized user interface. In contrast, the latter can formulate constraints that cannot be represented formally by query answering approaches due to the limited expressiveness of formal languages. But it is not obvious how to take into account the background and common sense knowledge to get precise answers over structured data.
The objective of this workshop is to bring together researchers and developers working on question/query answering systems over structured or unstructured knowledge, and create a platform to grow potential collaborations in this multidisciplinary task.
Topics of interest include, but are not limited to, the following:
- Natural Language Processing based question answering
- Ontology based query answering
- Hybrid reasoning
- Information extraction over unstructured and structured data
- Applications of question answering
- Domain-specific question answering
- Temporal event extraction from tex
- Temporal reasoning for query answering
- Ontologies and knowledge graphs
- Biomedical text analysis
- Datasets combining structured and unstructured knowledge
Papers for the workshop should be submitted in PDF format via EasyChair at this link, selecting the track First International Workshop on Hybrid Question Answering with Structured and Unstructured Knowledge. Submitted papers must use the new ACM format published in ACM guidelines (download from here), selecting the generic “sigconf” sample . Submissions must be in English and not exceed 4-6 pages in length.
Papers must have not been previously published or be under review at another workshop. However, we encourage submissions that present summaries or highlights of work appearing elsewhere in longer form. Accepted papers will be published in a companion volume of the main proceedings of The Web Conference 2018. We inivite the authors of accepted papers follow this instructions to prepare the final version.
- Franz Baader, TU Dresden, Germany
- Brigitte Grau, LIMSI,CNRS, Université Paris Saclay, France
- Yue Ma, LRI, CNRS, Université Paris Sud, France
- Stefan Borgwardt, TU Dresden, Germany
- Sanjay Kamath, LRI/LIMSI, CNRS, Université Paris Sud, France
- Pierre Zweigenbaum, LIMSI, CNRS, Université Paris Saclay, France
- Meghyn Bienvenu, LIRMM, CNRS, France
- Elena Cabrio, Inria, CNRS, I3S, Université Côte d’Azur, France
- Dennis Diefenbach, Université Saint-Etienne, France
- Francesco Donini, Università della Tuscia, Italy
- Walter Forkel, TU Dresden, Germany
- Zhisheng Huang, Vrije University of Amsterdam, The Netherlands
- Jens Lehmann, University of Bonn, Germany
- Anne-Laure Ligozat, LIMSI, CNRS, Université Paris Saclay, France
- Raghava Mutharaju, GE Global Research Center, USA
- Jeff Pan, The University of Aberdeen, United Kingdom
- Anselmo Peñas, National Distance Learning University, Spain
- Guilin Qi, Southeast University, China
- Fathia Sais, LRI, CNRS, Université Paris Sud, France
- Fabian M. Suchanek, Télécom ParisTech, France
- Michaël Thomazo, INRIA Saclay, France
- Guohui Xiao, Free University of Bozen-Bolzano, Italy
Title: Semantic annotation in the biomedical domain: large-scale classification and BioASQ
Speaker: Prof. Eric Gaussier
Abstract: Semantic annotation in the biomedical domain raises the problem of classifying texts with large-scale taxonomies, a problem sometimes referred to as extreme classification. In this presentation, we will give an overview of this problem and the main solutions proposed, with a focus on textual collections and the BioASQ challenge.
Prof. Eric Gaussier is known for his work on the intersection of Artificial Intelligence (AI) and Data Science (DS), in particular for his contributions on models and alogrithms to extract information, insights and knowledge from data in various forms. He has worked on three main subfields of AI and DS: machine learning, information retrieval and computational linguistics. He is also interested in modeling how (textual) information is shared in social (content) networks, and how such networks evolve over time. More recently, He has also been working on improving job scheduling techniques through machine learning, and in learning representations for different types of sequences, as texts and Time series.
Title: Towards Component-based, domain-specific, efficient Question Answering Systems
Speaker: Dr. Andreas Both
Abstract: In the past, the research, as well as industry, brought Question Answering (QA) into daily use. However, there is still an obvious gap between the claim of providing access to any -- structured or unstructured -- knowledge stored in the world using an interface fitting the demands of regular users. On the one hand side, implementing Question Answering Systems is still hard and time-consuming, on the other hand side, the QA community is still struggling on defining a common ground for collaboration across research fields regarding, for example, realistic benchmarks, maintainability, and broad coverage of knowledge sources. In the talk challenges of Question Answering will be highlight w.r.t. hybrid QA, domain-specific QA, cross knowledge base QA, etc. Particularly the industry perspective is also presented while aiming at a Question Answering platform which can be assembled from industry components as well as components of the research community. First steps towards this long-term vision are provided by the Qanary framework and similar frameworks aiming at a collaborative approach for the development QA systems which should lead to effective implementations, improved research results as well as a platform economy for QA. Such a platform would lead industry to a tighter collaboration while academics would have the opportunity of accessing precious data for further improvements.
Dr. Andreas Both is a computer scientist dedicated to applied research in an industrial context, in particular, data-driven processes, data integration, information retrieval applications and web engineering. Currently, he is Head of Architecture, Web Technology and IT Research at DATEV eG a German company dedicated to business software. He commits himself to advance in using the World Wide Web (WWW) as knowledge base and developing the next generation of Web applications to open the capabilities of the WWW for both industry and users. Since June 2016 Andreas Both is active as member of the WDAqua advisory board.
For details about traveling to Lyon, accommodation, and registration, please see the web pages of The Web Conference 2018.
- 09:00-10:00 (Invited talk) Towards Component-based, Domain-specific, Efficient Question Answering Systems. Andreas Both
- 10:00-10:20 WDAqua-core1: a Question Answering service for RDF Knowledge Bases. Dennis Diefenbach, Kamal Singh and Pierre Maret.
- 11:00-11:20 Multi-turn QA: A RNN Contextual Approach to Intent Classification for Goal-oriented Systems. Martino Mensio, Giuseppe Rizzo and Maurizio Morisio.
- 11:20-11:40 Verification of the Expected Answer Type for Biomedical Question Answering. Sanjay Kamath, Brigitte Grau, Yue Ma
- 11:40-12:00 A Factoid Question Answering System for Vietnamese. Phuong Le-Hong and Duc-Thien Bui.
- 12:00-12:20 A corpus for Hybrid Question Answering Systems. Brigitte Grau and Anne-Laure Ligozat.
- 13:40-14:40 (Invited talk) Semantic annotation in the biomedical domain: large-scale classification and BioASQ. Eric Gaussier
- 14:40-15:00 Query Expansion with Neural Question-to-Answer Translation for FAQ-based Question Answering. Atsushi Otsuka, Kyosuke Nishida, Katsuji Bessho, Hisako Asano and Junji Tomita.
- 15:30-15:50 Patient Selection for Clinical Trials Using Temporalized Ontology-Mediated Query Answering. Franz Baader, Stefan Borgwardt and Walter Forkel.
- 15:50-16:10 TempQuestions: A Benchmark for Temporal Question Answering. Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy, Jannik Stroetgen and Gerhard Weikum.
- 16:10-17:00 Discussion