2^nd International Workshop on Deep Learning for Question Answering

Question Answering System (QAS) is an important area in Artificial Intelligence. Generating automatic response is a fastidious and time-consuming task for there exists only some very general approaches to understand the intent of users. Question Answering (QA) is applied in many domain applications such as medical, finance, e-commerce, etc. Given a list of documents, a QAS can provide the right answer to the query pose in natural language. It combines natural language processing (NLP), information retrieval (IR) and knowledge representation and reasoning (KRR) as a relevant component for this process. The general process of QA is composed of different steps: (i) user query, (ii) question analysis (simple or complex query, open or closed domain, linguistic layer, semantic layer, etc), (iii) answer retrieval, and (iv) answer extraction from a set of candidate ones. All these steps are important to answer correctly, precisely and briefly to the user native language question. The answer can refer to a term, a sentence, an image, an audio, a video or to the full textual document.

Recent Deep Learning approaches and information retrieval are implemented in order to reason over the questions and its links with the corresponding response. Modern NLP techniques makes it possible for computers to read and interpret text, hear and understand speech, measure sentiment, and determine which parts in a document are important.

Another important aspect of QAS is the integration of knowledge graphs (KGs) as a new dimension to provide a concise answer issued from the KG. KG is graph-based data model that structure and store real-world entities (abstract concepts) and their relationships (hierarchical and associative) in a graph. The KG is the most suitable and beneficial way to solve many challenging problems related to information domain.

The second edition of this workshop aims at highlighting recent and future advances on question answering systems over structured semantic and unstructured textual data and to demonstrate the role of deep learning algorithms to enrich this process. In addition to that, the goal of this workshop is to bring together an area for experts from industry, science and academia to exchange ideas and discuss results of on-going research in Question Answering approaches.

This workshop is well closed to the relevant topics of the International Conference KGSWC-2022 such as Machine Learning, Information Retrieval and natural language processing and understanding, Knowledge Representation, etc. KGSWC-2022 will offer us the opportunity to exchange novel findings in the field of question/query answering systems over structured or unstructured knowledge with international scientists. It will be a pleasure to be among KGSWC 2022 workshops. Topics of interests: We invite the submission of original works that is related, but are not limited, to the topics below: 

• Question answering over Linked Data 

• Knowledge Graphs for Question Answering 

• Complex Question Answering over texts and linked data 

• Reasoning for Complex Question Answering 

• Natural Language Processing based question answering 

• Hybrid text and knowledge graph reasoning 

• SPARQL query pattern generation 

• Natural language querying of RDF exposed as Linked Data 

• Ontology-based query answering 

• Visual Question Answering 

• Image question answering 

• Audio and Speech Question Answering 

• Video Question Answering 

• Datasets combining structured and unstructured knowledge 

• Applications of question answering 

• and so on. 

Submission: 

The workshop is open to submit unpublished work resulting from researches that present original scientific results, methodological aspects, concepts and approaches. All submissions must be PDF documents written in English and formatted according to CEUR-WS   CEURART style. Templates are available for LaTeX and DOCX/ODT, for single column layout.

.

We welcome the following types of contributions:

Full research papers (10-15 pages): Finished or consolidated R&D works, to be included in one of the Workshop topics

Short papers (4-6 pages): Ongoing works with relevant preliminary results, opened to discussion.

At least one author of each accepted paper must register for the workshop, in order to present the paper, there, and to the conference. For further instructions please refer to the KGSWC 2022 page. 

Papers are to be submitted through the workshop's EasyChair submission page.

The Submission Web page for IWDLQ-2022 is   https://easychair.org/conferences/?conf=iwdlq2022

Publication:

All accepted workshop papers will be published in CEUR Proceedings. The best papers from this workshop may be included in the supplementary proceedings of KGSWC 2022.

Organizing committee:

Sarra BEN ABBES, Research Scientist, ENGIE-France: sarra.ben-abbes@external.engie.com 

Rim Hantach, Research Scientist, ENGIE-France: rim.hantach@external.engie.com 

Philippe Calvez, Research Lab Manager, ENGIE-France: philippe.calvez1@engie.com 

Keynote Speakers: 

–TBD 

Program Committee: 

– TBD