The Forest Convolutional Network: Compositional Distributional Semantics with a Neural Chart and without Binarization

Phong Le, Willem Zuidema

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

Abstract

According to the principle of compositionality, the meaning of a sentence is computed from the meaning of its parts and the way they are syntactically combined. In practice, however, the syntactic structure is computed by automatic parsers
which are far-from-perfect and not tuned to the specifics of the task. Current recursive neural network (RNN) approaches for computing sentence meaning therefore run into a number of practical difficulties, including the need to carefully select a parser appropriate for the task, deciding how and to what extent syntactic context modifies the semantic composition function, as well as on how to transform parse trees to conform to the branching settings (typically, binary branching) of the RNN. This paper introduces a new model, the Forest Convolutional Network, that avoids all of these challenges, by taking a parse forest as input, rather than a single tree, and by allowing arbitrary branching factors. We report improvements over the state-of-the-art in sentiment analysis and question classification.
Original languageEnglish
Title of host publicationProceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Place of PublicationLisbon, Portugal
PublisherAssociation for Computational Linguistics
Pages1155-1164
Number of pages10
DOIs
Publication statusPublished - Sep 2015
Event2015 Conference on Empirical Methods in Natural Language Processing - Lisbon, Portugal
Duration: 17 Sep 201521 Sep 2015
http://www.emnlp2015.org/

Conference

Conference2015 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2015
Country/TerritoryPortugal
CityLisbon
Period17/09/1521/09/15
Internet address

Fingerprint

Dive into the research topics of 'The Forest Convolutional Network: Compositional Distributional Semantics with a Neural Chart and without Binarization'. Together they form a unique fingerprint.

Cite this