Universiteit van Amsterdam

Events

Institute for Logic, Language and Computation

Please note that this newsitem has been archived, and may contain outdated information or links.

11-15 July 2016, NASSLLI workshop on Statistical and Logical Models of Meaning (SaLMoM), Rutgers University, New Jersey, USA

Date: 11-15 July 2016
Location: Rutgers University, New Jersey, USA
Deadline: 1 April 2016

Mathematical models of natural language semantics oscillate between the two opposing approaches of word-based statistical and sentence-based compositional. Word-based models rely on the ideas of Harris and Firth that words occurring in similar contexts have similar meanings. Compositional models, in the sense of Montague 1970, systematically associate the steps of a syntactic derivation with semantic operations acting on the interpretations of the constituents. This workshop is an attempt to bring together active researchers of these seemingly separate approaches to address problems of both theoretical and practical nature.

One major goal is to introduce the statistical researchers to the advanced type-logical techniques that have been developed to handle challenging grammatical phenomena; the second one is to help the researchers of the logical field to enhance their systems with vector representations. The overall goal is to help both groups collaborate to develop systems where both word vectors and complex grammatical structures can be reasoned about in a compositional and computationally tractable way.

For more information, see https://sites.google.com/site/statlogmeaning/.

We invite submissions in the form of 2-page abstracts on topics relating statistical and logical models of natural language. This can be a summary of an already published paper or a new contribution. Submissions will be evaluated as to their potential for establishing meaningful links between the logical and statistical approaches. Deadline: April 1st 2016. Submission webpage: https://easychair.org/conferences/?conf=salmom2016.

Please note that this newsitem has been archived, and may contain outdated information or links.