ACL-IJCNLP 2009 Workshop:
KRAQ09: Knowledge and Reasoning for Answering Questions
Singapore, 6 August, 2009
Held in conjunction with ACL-AJCNLP 2009
3-5 August, 2009
Submission deadline EXTENDED to May 8th !!
This workshop is the fifth of a series, it follows :
KRAQ05 (IJCAI 2005 Edinburgh, UK).
KRAQ06 (EACL 2006, Trento, Italy).
KRAQ07 (IJCAI 2007, Hyderabad, India).
KRAQ08 (COLING 2008, Manchester, UK)
Call for papers
The introduction of reasoning capabilities in question-answering (QA) systems appeared in the late 70s. A second generation of QA systems, aimed at being cooperative, emerged in the late 80s - early 90s. In these systems, quite advanced reasoning models were developed on closed domains to go beyond the production of direct responses to a query, in particular when the query has no response or when it contains misconceptions. More recently, systems such as JAVELIN, Inference WEB or Cogex, operating over open domains, integrated gradually inferential components, but not as advanced as those of the 90s. Performances of these systems in the recent TREC-QA tracks show that reasoning components substantially improve the response relevance and accuracy. They can also potentially be much more cooperative. However, there is still a long way before being able to produce accurate, cooperative and robust QA systems, because of the very large complexity of natural systems and of the need to make several communities work together on common grounds.
Recent foundational, methodological and technological developments in knowledge representation (e.g. ontologies, knowledge bases incorporating various forms of incompleteness or uncertainty), in advanced reasoning forms (e.g. data fusion-integration, argumentation, decision theory, fuzzy logic, incomplete knowledge bases, etc.), in advanced language processing resources and techniques (for question processing as well as for generating responses) including semantic role labelling and the recognition and resolution of temporal and spatial expressions, and recent progress in HLT and formal pragmatics (user models, intentions, etc.) make it possible to foresee the elaboration of much more accurate, cooperative and robust systems dedicated to answering questions from multimedia supports or from textual data, from e.g. online texts or web pages, operating either on open or closed domains. The user interface aspects (input, output (e.g. SMS or advanced interfaces), on line help, dialogue, etc.) are also crucial for the viability of such systems.
The workshop will be organized around a few major questions of interest to a number of AI, NLP, linguistics, HLT and pragmatics people. The workshop will be focussed on models for intelligently and cooperatively responding to the user. This includes areas such as AI models for processing data coming e.g. from search engines and models that provide users with explanations and arguments about response contents and the way they have been elaborated.
Besides language processing and AI, we open this workshop to topics of interest that include user interfaces and dialogue, multimedia QA, new types of applications and evaluation techniques.
We invite papers on any research topic related to question answering and reasoning. In this call we especially focus on:
New types of questions and related KR, pragmatic and linguistic paradigms:
procedural questions (how), causal questions (why), opinion questions, etc.;
Language processing: question processing, response production, semantic role labelling for QA and related marks, reasoning with lexical resources, textual inference, response production (planning and argumentation), language generation (e.g. lexical choice, templates), explanation production (showing sources and inferences, reporting data incompleteness, etc.);
Reasoning aspects: information fusion-integration, summarization and intensional answers, detecting and resolving query failure (due to e.g. incomplete data, misconceptions or false presuppositions), reasoning under uncertainty or with incomplete knowledge, models for explanation production and argumentation, levels of knowledge involved (e.g. ontologies, domain knowledge);
Pragmatic dimensions of intelligently answering questions: user intentions, plans and goals recognition and production, conversational implicatures in responses, principles for the design of cooperative systems;
User assistance: it is most important to tailor QA systems with user profiles, and to introduce dialogue capabilities when appropriate. The communication media should also be investigated in more depth, be it SMS or advanced interfaces;
Applications: multimedia question answering, where you question a more or less formal representation of the media objects, spoken question answering (increasing uncertainty caused by the speech recognition), question answering of semi-structured documents such as Wikipedia, legislation;
Evaluation: end-to-end evaluation of complex question types, intrinsic evaluation of inference methods, data-intensive vs knowledge-intensive methods, evaluation of portability techniques for closed domains.
The goal of the KRAQ 2009 workshop is to enhance cooperation between participants with an AI background and the NLP, HLT and question-answering communities. Contributors must be opened to interactions with the different workshop areas. The programme committee will take care of having a balanced number of papers from the different areas concerned.
long papers (max. 8 pages, 30 mns presentation) that include established results,
short papers (max. 5 pages including references, 15 mns presentation) describing projects or ongoing research and
posters (max. 3 pages including references, flash oral presentation: 5mns) that describe projects that started or ideas being investigated. The objective being to
organize a small forum on QA.
Papers must be sent in .pdf format at both addresses: email@example.com and firstname.lastname@example.org.
Since reviewing is blind, please make sure to include your name, and postal and email addresses in the body of the message,
specify the type of paper (full, short or poster) and the subject of the message must be 'KRAQ09 submission'.
The format to use for papers and abstracts is the same as for ACL 2009,
All papers are blinded for review. The title page includes the following information:
Topic(s) of the above list, as appropriate
Abstract (short summary up to 5 lines).
May 8th: paper submissions June 1st: acceptance/rejection notification June 7th: final papers due, camera-ready manuscript sent for printing by organizers.
All accepted papers (long, short and posters) will be published in the workshop proceedings.
Patrick Saint-Dizier CNRS
Department of Computer Science
Katholieke Universiteit Leuven
Sivaji Bandyopadhyay (India)
Johan Bos (Italy)
Gosse Bouma (The Netherlands)
Brigitte Grau (France)
Kentaro Inui (Japan)
Sanaee Kawtrakul (Thailand)
Jochen Leidner (USA)
Sien Moens (Belgium)
Matteo Negri (Italy)
Silvia Quarteroni (Italy)
Alan Ramsay (UK)
Patrick Saint-Dizier (France)
Tomek Strzalkowski (USA)
Michael Wiegand (Germany)