Bridging CNNs, RNNs, and Weighted Finite-State Machines

Roy Schwartz, Sam Thomson, Noah A. Smith


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.
Anthology ID:
P18-1028
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
295–305
Language:
URL:
https://aclanthology.org/P18-1028
DOI:
10.18653/v1/P18-1028
Bibkey:
Cite (ACL):
Roy Schwartz, Sam Thomson, and Noah A. Smith. 2018. Bridging CNNs, RNNs, and Weighted Finite-State Machines. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 295–305, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Bridging CNNs, RNNs, and Weighted Finite-State Machines (Schwartz et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1028.pdf
Note:
 P18-1028.Notes.pdf
Poster:
 P18-1028.Poster.pdf
Data
SST