@inproceedings{shen-etal-2018-baseline,
title = "Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms",
author = "Shen, Dinghan and
Wang, Guoyin and
Wang, Wenlin and
Min, Martin Renqiang and
Su, Qinliang and
Zhang, Yizhe and
Li, Chunyuan and
Henao, Ricardo and
Carin, Lawrence",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1041",
doi = "10.18653/v1/P18-1041",
pages = "440--450",
abstract = "Many deep learning architectures have been proposed to model the \textit{compositionality} in text sequences, requiring substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the added value of sophisticated compositional functions. In this paper, we conduct a point-by-point comparative study between Simple Word-Embedding-based Models (SWEMs), consisting of parameter-free pooling operations, relative to word-embedding-based RNN/CNN models. Surprisingly, SWEMs exhibit comparable or even superior performance in the majority of cases considered. Based upon this understanding, we propose two additional pooling strategies over learned word embeddings: (\textit{i}) a max-pooling operation for improved interpretability; and (\textit{ii}) a hierarchical pooling operation, which preserves spatial ($n$-gram) information within text sequences. We present experiments on 17 datasets encompassing three tasks: (\textit{i}) (long) document classification; (\textit{ii}) text sequence matching; and (\textit{iii}) short text tasks, including classification and tagging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2018-baseline">
<titleInfo>
<title>Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dinghan</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoyin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenlin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="given">Renqiang</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qinliang</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yizhe</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Henao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Carin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the added value of sophisticated compositional functions. In this paper, we conduct a point-by-point comparative study between Simple Word-Embedding-based Models (SWEMs), consisting of parameter-free pooling operations, relative to word-embedding-based RNN/CNN models. Surprisingly, SWEMs exhibit comparable or even superior performance in the majority of cases considered. Based upon this understanding, we propose two additional pooling strategies over learned word embeddings: (i) a max-pooling operation for improved interpretability; and (ii) a hierarchical pooling operation, which preserves spatial (n-gram) information within text sequences. We present experiments on 17 datasets encompassing three tasks: (i) (long) document classification; (ii) text sequence matching; and (iii) short text tasks, including classification and tagging.</abstract>
<identifier type="citekey">shen-etal-2018-baseline</identifier>
<identifier type="doi">10.18653/v1/P18-1041</identifier>
<location>
<url>https://aclanthology.org/P18-1041</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>440</start>
<end>450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
%A Shen, Dinghan
%A Wang, Guoyin
%A Wang, Wenlin
%A Min, Martin Renqiang
%A Su, Qinliang
%A Zhang, Yizhe
%A Li, Chunyuan
%A Henao, Ricardo
%A Carin, Lawrence
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F shen-etal-2018-baseline
%X Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the added value of sophisticated compositional functions. In this paper, we conduct a point-by-point comparative study between Simple Word-Embedding-based Models (SWEMs), consisting of parameter-free pooling operations, relative to word-embedding-based RNN/CNN models. Surprisingly, SWEMs exhibit comparable or even superior performance in the majority of cases considered. Based upon this understanding, we propose two additional pooling strategies over learned word embeddings: (i) a max-pooling operation for improved interpretability; and (ii) a hierarchical pooling operation, which preserves spatial (n-gram) information within text sequences. We present experiments on 17 datasets encompassing three tasks: (i) (long) document classification; (ii) text sequence matching; and (iii) short text tasks, including classification and tagging.
%R 10.18653/v1/P18-1041
%U https://aclanthology.org/P18-1041
%U https://doi.org/10.18653/v1/P18-1041
%P 440-450
Markdown (Informal)
[Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms](https://aclanthology.org/P18-1041) (Shen et al., ACL 2018)
ACL
- Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Chunyuan Li, Ricardo Henao, and Lawrence Carin. 2018. Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 440–450, Melbourne, Australia. Association for Computational Linguistics.