SIGLEX has currently identified 107 events (conferences and workshops) as having special interest to SIGLEX members. You can search this list by keywords or dates. You can also suggest an event to be added to this list. Proceedings of many of these workshops and conferences can be found at the ACL SIGLEX anthology. (Note that search functionality is an implied boolean AND that examines available thumbnail descriptions.)

Search terms: Year:

upcoming past all events SIGLEX events hide all

2nd Workshop on Text Meaning and Interpretation

Workshop at ACL 2004, 2004-07-25, Barcelona, Spain. (Proceedings) (34)

This aims to: re-establish the research community of knowledge-based interpretation of text meaning; explicate the implicit treatments of meaning in current knowledge-lean approaches and how they and knowledge-rich methods can work together; and emphasize the construction of systems that extract, represent, manipulate, and interpret the meaning of text (rather than theoretical and formal methods in semantics). Most, if not all, high-end NLP applications—such as machine translation, question answering and text summarization, stand to benefit from being able to use text meaning in their processing. But the bulk of work in the field in recent years has not pertained to treatment of meaning. The main reason given is the complexity of the task of comprehensive meaning analysis and interpretation. Computational linguistics has always been interested in meaning, of course. The tradition of formal semantics, logics, and common-sense reasoning system has been continuously maintained for many years. But also, much work has been devoted to building practical, increasingly broad-coverage meaning-oriented analysis and synthesis systems. Lexical semantics has made significant progress in theories, description, and processing. Formal aspects of ontology work have also been studied. The Semantic Web has further popularized the need for automatic extraction, representation, and manipulation of text meaning: for the Semantic Web to really succeed, capability of automatically marking text for content is essential, and this cannot be attained reliably using only knowledge-lean, semantics-poor methods.