May 31 - June 1, 1998

Granada, Spain

The development of natural language applications which handle multi-lingual and multi-modal information is the next major challenge facing the field of computational linguistics. Over the past 50 years, a variety of language-related capabilities has been developed in areas such as machine translation, information retrieval, and speech recognition, together with core capabilities such as information extraction, summarization, parsing, generation, multimedia planning and integration, statistics-based methods, ontologies, lexicon construction and lexical representations, and grammar. The next few years will require the extension of these technologies to encompass multi-lingual and multi-modal information.

Extending current technologies will require integration of the various capabilities into multi-functional natural language systems. However, there is today no clear vision of how these technologies could or should be assembled into a coherent framework. What would be involved in connecting a speech recognition system to an information retrieval engine, and then using machine translation and summarization software to process the retrieved text? How can traditional parsing and generation be enhanced with statistical techniques? What would be the effect of carefully crafted lexicons on traditional information retrieval?

At this workshop, an international panel of invited experts will consider these questions in an attempt to identify the most effective future directions of computational linguistics research--especially in the context of the need to handle multi-lingual and multi-modal information. The workshop will include ample time for discussion. A report summarizing the discussions at Granada will be made available to the community at large as well as to relevant organizations and funders. A follow-up workshop, intended to open the discussion to the computational linguistics community as a whole, will be held at Coling/ACL.

The workshop will focus on the following fundamental questions:

1. What is the current level of capability in each of the major areas of the field dealing with language and related media of human communication?
2. How can (some of) these functions be integrated in the near future, and what kind of systems will result?
3. What are the major considerations for extending these functions to handle multi-lingual and multi-modal information, particularly in integrated systems of the type envisioned in (2)?

In particular, we will consider these questions in relation to the following areas:

• multi-lingual resources (lexicons, ontologies, corpora, etc.)
• information retrieval, especially cross-lingual and cross-modal
• machine translation
• automated (cross-lingual) summarization and information extraction
• multimedia communication, in conjunction with text
• evaluation and assessment techniques for each of these areas
• methods and techniques (both statistics-based and linguistics-based) of pre-parsing, parsing, generation, information acquisition, etc.

Robert Frederking, Carnegie-Mellon University, USA
Eduard Hovy, USC Information Sciences Institute, USA
Nancy Ide, Vassar College, USA
Joseph Mariani, LIMSI/CNRS, France
Angel Martin Municio, Real Academia de Ciencias, Madrid, Spain
Antonio Zampolli, Istituto di Linguistica Computazionale/Pisa, Italy