@inproceedings{jiang-etal-2020-cold,
title = "Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks",
author = "Jiang, Chengyue and
Zhao, Yinggong and
Chu, Shanbo and
Shen, Libin and
Tu, Kewei",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.258",
doi = "10.18653/v1/2020.emnlp-main.258",
pages = "3193--3207",
abstract = "Neural networks can achieve impressive performance on many natural language processing applications, but they typically need large labeled data for training and are not easily interpretable. On the other hand, symbolic rules such as regular expressions are interpretable, require no training, and often achieve decent accuracy; but rules cannot benefit from labeled data when available and hence underperform neural networks in rich-resource scenarios. In this paper, we propose a type of recurrent neural networks called FA-RNNs that combine the advantages of neural networks and regular expression rules. An FA-RNN can be converted from regular expressions and deployed in zero-shot and cold-start scenarios. It can also utilize labeled data for training to achieve improved prediction accuracy. After training, an FA-RNN often remains interpretable and can be converted back into regular expressions. We apply FA-RNNs to text classification and observe that FA-RNNs significantly outperform previous neural approaches in both zero-shot and low-resource settings and remain very competitive in rich-resource settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2020-cold">
<titleInfo>
<title>Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengyue</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinggong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanbo</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libin</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kewei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural networks can achieve impressive performance on many natural language processing applications, but they typically need large labeled data for training and are not easily interpretable. On the other hand, symbolic rules such as regular expressions are interpretable, require no training, and often achieve decent accuracy; but rules cannot benefit from labeled data when available and hence underperform neural networks in rich-resource scenarios. In this paper, we propose a type of recurrent neural networks called FA-RNNs that combine the advantages of neural networks and regular expression rules. An FA-RNN can be converted from regular expressions and deployed in zero-shot and cold-start scenarios. It can also utilize labeled data for training to achieve improved prediction accuracy. After training, an FA-RNN often remains interpretable and can be converted back into regular expressions. We apply FA-RNNs to text classification and observe that FA-RNNs significantly outperform previous neural approaches in both zero-shot and low-resource settings and remain very competitive in rich-resource settings.</abstract>
<identifier type="citekey">jiang-etal-2020-cold</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.258</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.258</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3193</start>
<end>3207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks
%A Jiang, Chengyue
%A Zhao, Yinggong
%A Chu, Shanbo
%A Shen, Libin
%A Tu, Kewei
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F jiang-etal-2020-cold
%X Neural networks can achieve impressive performance on many natural language processing applications, but they typically need large labeled data for training and are not easily interpretable. On the other hand, symbolic rules such as regular expressions are interpretable, require no training, and often achieve decent accuracy; but rules cannot benefit from labeled data when available and hence underperform neural networks in rich-resource scenarios. In this paper, we propose a type of recurrent neural networks called FA-RNNs that combine the advantages of neural networks and regular expression rules. An FA-RNN can be converted from regular expressions and deployed in zero-shot and cold-start scenarios. It can also utilize labeled data for training to achieve improved prediction accuracy. After training, an FA-RNN often remains interpretable and can be converted back into regular expressions. We apply FA-RNNs to text classification and observe that FA-RNNs significantly outperform previous neural approaches in both zero-shot and low-resource settings and remain very competitive in rich-resource settings.
%R 10.18653/v1/2020.emnlp-main.258
%U https://aclanthology.org/2020.emnlp-main.258
%U https://doi.org/10.18653/v1/2020.emnlp-main.258
%P 3193-3207
Markdown (Informal)
[Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks](https://aclanthology.org/2020.emnlp-main.258) (Jiang et al., EMNLP 2020)
ACL