SOPA: Bridging CnNs, RNNs, and weighted finite-state machines

Roy Schwartz, Sam Thomson, Noah A. Smith

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

18 Scopus citations

Abstract

Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model that aims to bridge these two approaches. SoPa combines neural representation learning with weighted finite-state automata (WFSAs) to learn a soft version of traditional surface patterns. We show that SoPa is an extension of a one-layer CNN, and that such CNNs are equivalent to a restricted version of SoPa, and accordingly, to a restricted form of WFSA. Empirically, on three text classification tasks, SoPa is comparable or better than both a BiLSTM (RNN) baseline and a CNN baseline, and is particularly useful in small data settings.

Original languageAmerican English
Title of host publicationACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages295-305
Number of pages11
ISBN (Electronic)9781948087322
StatePublished - 2018
Externally publishedYes
Event56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
Duration: 15 Jul 201820 Jul 2018

Publication series

NameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Country/TerritoryAustralia
CityMelbourne
Period15/07/1820/07/18

Bibliographical note

Publisher Copyright:
© 2018 Association for Computational Linguistics

Fingerprint

Dive into the research topics of 'SOPA: Bridging CnNs, RNNs, and weighted finite-state machines'. Together they form a unique fingerprint.

Cite this