ACL 2001 Workshop on HLT and KM

---

WORKSHOP ON HUMAN LANGUAGE TECHNOLOGY 
AND KNOWLEDGE MANAGEMENT

ACL'2001 Conference
Toulouse, France
July 6-7, 2001

Description

Human language technologies promise solutions to challenges in human computer interaction, information access, and knowledge management. Advances in technology areas such as indexing, retrieval, transcription, extraction, translation, and summarization offer new capabilities for learning, playing and conducting business. This includes enhanced awareness, creation and dissemination of enterprise expertise and know-how.

This workshop aimed to bring together the community of computational linguists working in a range of areas (e.g., speech and language processing, translation, summarization, multimedia presentation, content extraction, dialog tracking) both to report advances in human language technology, their application to knowledge management and to establish a road map for the Human Language Technologies for the next decade.  The road map will comprise an analysis of the present situation, a vision of where we want to be in ten years from now, and a number of inter-mediate milestones that would help in setting intermediate goals and in measuring our progress towards our goals.

The workshop was structured into two days, the first of which addressed new research in human language technology for knowledge management that addresses problems including but not limited to:

• Expert Discovery:  Modeling, cataloguing and tracking of distributed organizations and communities of experts.
• Knowledge Discovery:  Identification and classification of knowledge from unstructured multimedia data.
• Knowledge Sharing: Awareness of and access to enterprise expertise and know-how.

Human language technology promises solutions to these challenges through technologies such as:

• Automated retrieval, extraction, and enrichment of information and knowledge from multimedia, multilin-gual, and multiparty information sources.
• Translingual or crosslingual retrieval, presentation, and sharing of knowledge.
• Automated detection and tracking of emerging topics from unstructured multimedia data (e.g., documents, web, video news broadcasts).
• Use of knowledge sources to facilitate knowledge mapping and access (e.g., lexicosemantic such as Word-Net, semantic such as geospatial Gazetteers, semistructured such as thesauri, encyclopedia, fact books)
• Automated question-answering from heterogeneous source
• Intelligent tools that support the automated bibliometrics and document analysis/understanding in support of discovery of distributed experts and communities of expertise
• Summarization and presentation generation of knowledge (e.g., knowledge maps, lessons learned).
• Modeling of user knowledge, beliefs, plans, (dis)abilities and preferences from queries, created artifacts, and human computer interactions.

The second day of the workshop targeted the formulation and refinement of a road map for the Human Language Technologies for the next decade.  Participants helped formulate grand challenge problems, discuss possible data sets and/or evaluation metrics/methods that could form the basis of more scientific methods, articulate the role of and necessary advances in human language technology to solve these challenges, as well as identify and characterize early innovations and issues (e.g., robustness, scalability, ontology, privacy).

Program

Please note that this programme gives you access to

• The slides of the invited talk by Steffen Staab (there is a brief abstract in the proceedings)
• A corrected version of the paper by Nigel Dewdney et al (the version in the proceedings is corrupted)
• A draft summary of the discussions (HTML needs reformatting)

Program Committee

• Dr. Mark Maybury (Chair), The MITRE Corporation, maybury@mitre.org
• Niels Ole Bernsen (Co-chair), University of Southern Denmark, nob@nis.sdu.dk
• Steven Krauwer, ELSNET, U. Utrecht, steven.krauwer@let.uu.nl
• Irma Becerra-Fernandez, Florida International University, becferi@fiu.edu
• Paul Heisterkamp, Daimler-Chrysler Research Ulm, paul.heisterkamp@daimlerchrysler.com
• Arjan van Hessen, COMSYS / U. Twente, hessen@cs.utwente.nl
• Pierre Isabelle, XEROX Grenoble, pierre.isabelle@xrce.xerox.com
• Enrico Motta, The Open University, e.motta@open.ac.uk
• Jose Pardo, ELSNET, Univ.Politecnica Madrid, pardo@die.upm.es
• Oliviero Stock, IRST Trento, stock@itc.it
• Henry Thompson HCRC LTG, University of Edinburgh, ht@cogsci.ed.ac.uk
• Hans Uszkoreit, DFKI Saarbruecken, uszkoreit@dfki.de
• Yorick Wilks, University of Sheffield, yorick@dcs.shef.ac.uk
• Rick Wojcik, Boeing Phantom Works, richard.h.wojcik@boeing.com
• Antonio Zampolli, ELSNET, U. Pisa, pisa@ilc.pi.cnr.it