A comparison between CNNs and WFAs for Sequence Classification

Ariadna Quattoni, Xavier Carreras


Abstract
We compare a classical CNN architecture for sequence classification involving several convolutional and max-pooling layers against a simple model based on weighted finite state automata (WFA). Each model has its advantages and disadvantages and it is possible that they could be combined. However, we believe that the first research goal should be to investigate and understand how do these two apparently dissimilar models compare in the context of specific natural language processing tasks. This paper is the first step towards that goal. Our experiments with five sequence classification datasets suggest that, despite the apparent simplicity of WFA models and training algorithms, the performance of WFAs is comparable to that of the CNNs.
Anthology ID:
2020.sustainlp-1.21
Volume:
Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing
Month:
November
Year:
2020
Address:
Online
Editors:
Nafise Sadat Moosavi, Angela Fan, Vered Shwartz, Goran Glavaš, Shafiq Joty, Alex Wang, Thomas Wolf
Venue:
sustainlp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
159–163
Language:
URL:
https://aclanthology.org/2020.sustainlp-1.21
DOI:
10.18653/v1/2020.sustainlp-1.21
Bibkey:
Cite (ACL):
Ariadna Quattoni and Xavier Carreras. 2020. A comparison between CNNs and WFAs for Sequence Classification. In Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing, pages 159–163, Online. Association for Computational Linguistics.
Cite (Informal):
A comparison between CNNs and WFAs for Sequence Classification (Quattoni & Carreras, sustainlp 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.sustainlp-1.21.pdf
Video:
 https://slideslive.com/38939443
Data
SSTSST-2