News and Events: Conferences

Please note that this newsitem has been archived, and may contain outdated information or links.

17 or 18 September 2015, EMNLP Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem 2015), Lisbon

Date: 17 or 18 September 2015
Location: Lisbon
Deadline: 28 June 2015

Improved computational models of semantics hold great promise for applications in language technology, be it semantics at the lexical level, sentence level or discourse level. Large-scale corpora with corresponding annotations (word senses, propositions, attributions and discourse relations) are making it possible to develop statistical models for many tasks and applications. However, developments in lexical and sentence-level semantics remain largely distinct from those in discourse semantics. This workshop aims at bridging this gap by bringing together researchers to discuss how multiple levels of semantics can be integrated and implemented in various applications.

Our goal is to gather and showcase theoretical and computational approaches to joint models of semantics, and applications that incorporate multi-level semantics. We hope to bring together researchers from various areas: computational linguistics who strive for more expressive models of language understanding, linguists and cognitive scientists interested in aspects of representing text with multiple levels of semantics, machine learning researchers interested in joint inference over different types of semantic cues, and also researchers who are interested in applications that require or will benefit from multi-level semantics. A dialog between researchers has great potential to advance work in each of these areas and bring about more powerful and enriched models of text semantics.

For more information, see http://homepages.inf.ed.ac.uk/mroth/LSDSem/

The Programme Committee cordially invites all researchers to submit their papers for presentation. Submission deadline is 28 June 2015.

Please note that this newsitem has been archived, and may contain outdated information or links.