3rd international workshop on
KNOWLEDGE and REASONING for ANSWERING QUESTIONS (KRAQ'07)
Special focus on knowledge explicitation, explanation, and argumentation in responses.
Hyderabad, January 6th, 2007
10:30 Learning by reading: two experiments
(Rutu Mulkar, Eduard Hovy, Hans Chalupsky, Chin-Yew Lin)
11:00 Knowledge assessment: A model logic approach
(Vineet Padmanabhan, Guido Governatori, Kaile Su)
11:30 Hybrid knowledge model for relevant information retrieval
(Reena T. N. Shetty, Pierre-Michel Riccio, Joël Quinqueton)
12:00 Using human factors, reasoning and text processing for hypotheses validation ()
14:00 A knowledge based approach to answering novel questions
(Shaw-Yi Chaw, Bruce Porter)
14:30 Reasoning with incomplete data in a restricted domain QA system
(Srinivasa Rao, Sivaji Bandyopadhyay)
15:00 Beyond corpus lookup: Towards Heuristic Reasoning with Text
15:30 Coffee break
16:00 A hybrid unification method for question answering in closed domains
(Abolfazl Keighobadi Lamjiri, Leila Kosseim, Thiruvengadam Radhakrishnan)
16:30 Filtering and fusion of question answering streams by robust textual inference
17:00 (Reserve paper) An empirical analysis of argument coherence in procedural texts
(Patrick Saint Dizier)
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), in advanced language processing resources and techniques (for question processing as well as for generating responses), 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 textual data, from e.g. online texts or web pages, operating either on open or closed domains.
The workshop will be organized around a few major questions of interest to a number of AI, NLP, 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.
One main question is the characterization of those reasoning procedures that need to be developed to answer questions, either on closed or on open domains, so that the user exactly percieves the appropriateness of the response (e.g. when the response is not the one he expects). Another perspective is the role of pragmatics as a means, for example, to better capture the user's goals and intentions from his query, and therefore to better organize the response and the arguments that justify the response. Pragmatics is also of importance to better analyse the potential implicatures the user may draw from responses, in particular when the response is not direct. Finally, and obviously, natural language generation, in connection with the inferantial mechanisms that lead to the answer, is a major point.
List of topics (not exhaustive)
- Question processing: new types of questions (why, how, opinion, etc.),
reformulation and disambiguisation strategies, interpretation models,
- Reasoning aspects:
* information fusion-integration,
* detecting and resolving query failure (due to e.g. incomplete data, misconceptions or false presuppositions),
* decision making,
* reasoning under uncertainty or with incomplete knowledge,
* models for explaining and arguing about answers.
- Knowledge representation and integration: (e.g. ontologies, domain knowledge).
- Flexible and interactive systems possibly including a user model, recommender systems,
- Pragmatic dimensions (user intentions, plans and goals recognition and generation, conversational implicatures),
- Language processing:
* question processing,
* response production (planning and argumentation), language generation (e.g. lexical choice, planning), specific linguistic aspects of argumentation (e.g. marks, connectors),
* explanation production (showing sources and inferences, reporting data incompleteness, etc.), argumentation.
- Evaluation (e.g. component evaluation).
The goal of this workshop is to enhance
cooperation between participants with an AI background and the NLP community.
Contributors must be opened to interactions with the different workshop areas.
The programme committee will care to have a balanced number of participants
from the different areas concerned.
To encourage an athmosphere appropriate for a workshop, we plan to:
- have a 15mn discussion at the end of each session,
- have a panel on future directions of intelligent question-answering and on how the different disciplines can interact as optimally as possible,
- plan demos on portable machines.
We welcome short papers (max 4 pages), describing projects or ongoing research and long papers (max. 8 pages), that relate more established results. Papers must be sent in .pdf format. The format to use for papers and abstracts is the same as for IJCAI. Please follow the IJCAI formatting instructions and use the supplied Word templates or Latex sources. The title page (no separate title page is needed) should include the following information:
- Authors' names, affiliations, and email addresses
- Topic(s) of the above list, as appropriate
- Abstract (short summary up to 5 lines)
September 25: paper submissions, sent to both: firstname.lastname@example.org and
October 22: acceptance/rejection notification
November 1st: final papers due, camera-ready
Workshop co-chairs and contact persons:
Dr. Leila Amgoud and Dr.
Patrick Saint-Dizier (email@example.com, firstname.lastname@example.org)
IRIT-CNRS 118 route de Narbonne
31062 Toulouse cedex France
Leila Amgoud, IRIT-CNRS, France
Farah Benamara, IRIT, France
Johan Bos, University of Edinburgh, UK
Carlos Chesnevar, univ. Lleida, Spain
Ed Hovy, ISI, USA
Jacques Moeschler, univ. Genève, Switzerland
Ehud Reiter, University of Aberdeen, UK
Patrick Saint Dizier, IRIT, CNRS, France
Sudeshna Sarka, IIT Kharagpur, India
Guillermo Simari, UN. Del Sur, Argentina
Ingrid Zuckerman, Monash, Australia