@inproceedings{ma-etal-2020-mode,
title = "{MODE}-{LSTM}: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification",
author = "Ma, Qianli and
Lin, Zhenxi and
Yan, Jiangyue and
Chen, Zipeng and
Yu, Liuhong",
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.544",
doi = "10.18653/v1/2020.emnlp-main.544",
pages = "6705--6715",
abstract = "The central problem of sentence classification is to extract multi-scale n-gram features for understanding the semantic meaning of sentences. Most existing models tackle this problem by stacking CNN and RNN models, which easily leads to feature redundancy and overfitting because of relatively limited datasets. In this paper, we propose a simple yet effective model called Multi-scale Orthogonal inDependEnt LSTM (MODE-LSTM), which not only has effective parameters and good generalization ability, but also considers multiscale n-gram features. We disentangle the hidden state of the LSTM into several independently updated small hidden states and apply an orthogonal constraint on their recurrent matrices. We then equip this structure with sliding windows of different sizes for extracting multi-scale n-gram features. Extensive experiments demonstrate that our model achieves better or competitive performance against state-of-the-art baselines on eight benchmark datasets. We also combine our model with BERT to further boost the generalization performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2020-mode">
<titleInfo>
<title>MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianli</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenxi</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiangyue</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zipeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liuhong</namePart>
<namePart type="family">Yu</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>The central problem of sentence classification is to extract multi-scale n-gram features for understanding the semantic meaning of sentences. Most existing models tackle this problem by stacking CNN and RNN models, which easily leads to feature redundancy and overfitting because of relatively limited datasets. In this paper, we propose a simple yet effective model called Multi-scale Orthogonal inDependEnt LSTM (MODE-LSTM), which not only has effective parameters and good generalization ability, but also considers multiscale n-gram features. We disentangle the hidden state of the LSTM into several independently updated small hidden states and apply an orthogonal constraint on their recurrent matrices. We then equip this structure with sliding windows of different sizes for extracting multi-scale n-gram features. Extensive experiments demonstrate that our model achieves better or competitive performance against state-of-the-art baselines on eight benchmark datasets. We also combine our model with BERT to further boost the generalization performance.</abstract>
<identifier type="citekey">ma-etal-2020-mode</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.544</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.544</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>6705</start>
<end>6715</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification
%A Ma, Qianli
%A Lin, Zhenxi
%A Yan, Jiangyue
%A Chen, Zipeng
%A Yu, Liuhong
%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 ma-etal-2020-mode
%X The central problem of sentence classification is to extract multi-scale n-gram features for understanding the semantic meaning of sentences. Most existing models tackle this problem by stacking CNN and RNN models, which easily leads to feature redundancy and overfitting because of relatively limited datasets. In this paper, we propose a simple yet effective model called Multi-scale Orthogonal inDependEnt LSTM (MODE-LSTM), which not only has effective parameters and good generalization ability, but also considers multiscale n-gram features. We disentangle the hidden state of the LSTM into several independently updated small hidden states and apply an orthogonal constraint on their recurrent matrices. We then equip this structure with sliding windows of different sizes for extracting multi-scale n-gram features. Extensive experiments demonstrate that our model achieves better or competitive performance against state-of-the-art baselines on eight benchmark datasets. We also combine our model with BERT to further boost the generalization performance.
%R 10.18653/v1/2020.emnlp-main.544
%U https://aclanthology.org/2020.emnlp-main.544
%U https://doi.org/10.18653/v1/2020.emnlp-main.544
%P 6705-6715
Markdown (Informal)
[MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification](https://aclanthology.org/2020.emnlp-main.544) (Ma et al., EMNLP 2020)
ACL