KRAQ'06 KNOWLEDGE and REASONING for LANGUAGE PROCESSING
Trento, April 3rd, 2005, an EACL Workshop
The EACL KRAQ06 workshop will be hosted in conjunction with the 11th Conference of the European Chapter of the Association for Computational Linguistics that will take place April 3-7, 2006, in Trento, Italy.
Programme
8:45 - 9:00 Welcome
9: 00 - 9 : 30 Introductory presentation : Farah Benamara
Language and Reasoning for Question Answering: State of the Art and Future Directions
9 : 30 - 10: 00 Myroslava O. Dzikovska, Charles B. Callaway, Elaine Farrow
Interpretation and Generation in a Knowledge-Based Tutorial System
10 : 00 - 10 : 30 Matra Gatius and Maritxell Gonzàles
Using Application-Specific Ontologies To Improve Performance in a Bottom-up Parser
10 : 30 - 11: 00 Coffee break
11: 00 - 11 : 30 Marilisa Amoia and Claire Gardent
Adjective based inference
11: 30 - 12 : 00 Martin Magnusson
Natural Language Understanding using Temporal Action Logic
12:00 - 12: 30 Fiona McNeill and Harry Halpin and Ewan Klein and Alan Bundy
Merging Stories with Shallow Semantics
12:00 - 14: 30 Lunch
14 : 30 - 15: 30 Invited speaker: Gosse Bouma
Linguistic Knowledge and Question Answering.
15: 30 - 16: 00 Véronique Moriceau
Numerical Data Integration for Cooperative Question-Answering
16: 00 - 16: 30 Coffee break
16: 30 - 17: 00 Silvia Quarteroni and Suresh Manandhar
Incorporating User Models in Question Answering to Improve Readability
17: 00 - 17: 45 Invited speaker: Dominique Laurent
Industrial concerns of a Question-Answering system
17: 45 - 18: 00 Closing
Objectives
Recent foundational, methodological and
technological developments in advanced language processing resources and
techniques, knowledge representation, advanced reasoning forms not necessarily
based on unification, applied pragmatics, and recent progress in HLT make it
possible to foresee the elaboration of much more accurate, cooperative and
robust systems dedicated to NLP in general and to answering questions in
particular. The development of more robust evaluation techniques make it also
possible to identify results, weaknesses and future directions.
The 2006 version of this workshop will be
organized around major questions of interest to a number of
NLP, AI, HLT and pragmatics people. Besides
Question-Answering, which is a hot topic in this perspective, we want the
workshop to address any area of NLP that requires knowledge and reasoning to
perform better. We expect contributions on rapidly evolving areas, such as
question processing and interpretation, explanation production, user profiling,
dialogue, language generation, evaluation for advanced systems, pragmatics,
etc. For example, w.r.t. NLG, an important question concerns the language
models and techniques appropriate for producing responses which sound natural
for the user (relevant, fluid, of an appropriate granularity, with terms the
user understands, etc.).
List of topics
- Methodologies for integrating knowledge and
reasoning into NLP systems, expected results,
- Reasoning aspects:
* dedicated inference schemas (in semantics, in pragmatics and in interpretation phases)
* intelligent information processing, resolving redundancies or inconsistencies, e.g. via fusion in NLG,
* search criteria expansion models (e.g. relaxation techniques) in QA,
* inference in summarization,
* reasoning under uncertainty or with incomplete knowledge, e.g. in dialogue.
- Knowledge representation and integration:
* levels of knowledge involved in NLP (e.g. ontologies, domain knowledge), and their relations to language
* knowledge extraction models and techniques,
* coherence and integration.
- Flexible and interactive systems possibly including a user model,
- Pragmatic dimensions:
* user intentions, plans and goals recognition and generation,
* conversational implicatures,
* principles for the design of cooperative systems.
- Language processing:
* question processing,
* language generation (e.g. lexical choice, planning),
* use of language resources to develop reasoning schemas (e.g. lexical semantics relations)
* reasoning to resolve ambiguities or references,
* explanation production (showing sources and inferences, reporting data incompleteness, etc.), argumentation.
* intelligent language tutoring systems.
- Evaluation
* End-to-end evaluation,
* Intrinsic evaluation of inference methods,
* Data-intensive vs knowledge-intensive methods,
* portability techniques for closed domains.
Submission
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: reasoning and inference, NLP (among which
question processing and language generation), question-answering, human
language technology and pragmatics.
Although papers will obviously have a dominant
theme, it is important that they contain material from at least 2 topics of the
workshop.
Submission format:
We welcome original, unpublished, short papers
(max 3 to 5 pages, with a short oral presentation), describing projects or
ongoing research and long papers (6 to 8 pages), that relate more established
results. The format follows the guidelines of the main
conference which can be found at:
http://eacl06.itc.it/main/cfp.htm
Please, send your final file in .pdf form to the two co-chairs, as specified
below.
Each submission will be reviewed at least by two members of the programme committee. Accepted papers will be published in the workshop proceedings.
Dual submissions to the main EACL 2006 conference and this workshop are allowed; if you submit to the main session, do indicate this when you submit to the workshop.
If your paper is accepted for the main session, you should withdraw your paper from the workshop upon notification by the main session.
Deadlines:
January 6: paper submissions
January 27: acceptance/rejection notification
February 10: final papers due, camera-ready
3 April 2006:
Workshop
Workshop co-chairs and contact persons:
Dr. Farah Benamara and Dr.
Patrick Saint-Dizier (benamara@irit.fr, stdizier@irit.fr)
IRIT-CNRS 118 route de Narbonne
31062 Toulouse cedex France
Programme Committee
Farah Benamara, IRIT, France
Johan Bos, University of Edinburgh, UK
Eduard Hovy, ISI, USA
Daniel Kayser, LIPN, France
Asanee Kawtrakul, Kasererart univ. Thailand
Mark Maybury, The MITRE Corp., USA
Yuji Matsumoto, Nara, Japan
Marie-Francine Moens, KUL, Belgium
John Prager, IBM, USA
Bali Ranaivo, Univ. Sains Malaysia, Malaysia
Ehud Reiter, University of Aberdeen, UK
Patrick Saint Dizier, IRIT, CNRS, France
Sudeshna Sarkar, IIT Kharagpur, India
Mathiew Stone, Center of Cognitive Science, Rutgers, USA