Compositional Distributional Semantics with Long Short Term Memory

Phong Le, Willem Zuidema

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We are proposing an extension of the recursive neural network that makes use of a variant of the long short-term memory architecture. The extension allows information low in parse trees to be stored in a memory register (the ‘memory cell’) and used much later higher up in the parse tree. This provides a solution to the vanishing gradient problem and allows the network to capture long range dependencies. Experimental results show that our composition outperformed the traditional neural-network composition on the Stanford Sentiment Treebank.
Original languageEnglish
Title of host publicationProceedings of the Fourth Joint Conference on Lexical and Computational Semantics
Place of PublicationDenver, Colorado
PublisherAssociation for Computational Linguistics
Pages10-19
Number of pages10
DOIs
Publication statusPublished - Jun 2015
EventFourth Joint Conference on Lexical and Computational Semantics - Denver, United States
Duration: 4 Jun 20155 Jun 2015
https://sites.google.com/site/starsem2015/

Conference

ConferenceFourth Joint Conference on Lexical and Computational Semantics
Abbreviated titleSEM 2015
Country/TerritoryUnited States
CityDenver
Period4/06/155/06/15
Internet address

Fingerprint

Dive into the research topics of 'Compositional Distributional Semantics with Long Short Term Memory'. Together they form a unique fingerprint.

Cite this