@inproceedings{duan-etal-2021-enslm,
title = "{E}ns{LM}: Ensemble Language Model for Data Diversity by Semantic Clustering",
author = "Duan, Zhibin and
Zhang, Hao and
Wang, Chaojie and
Wang, Zhengjue and
Chen, Bo and
Zhou, Mingyuan",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.230",
doi = "10.18653/v1/2021.acl-long.230",
pages = "2954--2967",
abstract = "Natural language processing (NLP) often faces the problem of data diversity such as different domains, themes, styles, and so on. Therefore, a single language model (LM) is insufficient to learn all knowledge from diverse samples. To solve this problem, we firstly propose an autoencoding topic model with a mixture prior (mATM) to perform clustering for the data, where the clusters defined in semantic space describes the data diversity. Having obtained the clustering assignment for each sample, we develop the ensemble LM (EnsLM) with the technique of weight modulation. Specifically, EnsLM contains a backbone that is adjusted by a few modulated weights to fit for different sample clusters. As a result, the backbone learns the shared knowledge among all clusters while modulated weights extract the cluster-specific features. EnsLM can be trained jointly with mATM with a flexible LM backbone. We evaluate the effectiveness of both mATM and EnsLM on various tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duan-etal-2021-enslm">
<titleInfo>
<title>EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhibin</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaojie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengjue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyuan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Natural language processing (NLP) often faces the problem of data diversity such as different domains, themes, styles, and so on. Therefore, a single language model (LM) is insufficient to learn all knowledge from diverse samples. To solve this problem, we firstly propose an autoencoding topic model with a mixture prior (mATM) to perform clustering for the data, where the clusters defined in semantic space describes the data diversity. Having obtained the clustering assignment for each sample, we develop the ensemble LM (EnsLM) with the technique of weight modulation. Specifically, EnsLM contains a backbone that is adjusted by a few modulated weights to fit for different sample clusters. As a result, the backbone learns the shared knowledge among all clusters while modulated weights extract the cluster-specific features. EnsLM can be trained jointly with mATM with a flexible LM backbone. We evaluate the effectiveness of both mATM and EnsLM on various tasks.</abstract>
<identifier type="citekey">duan-etal-2021-enslm</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.230</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.230</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2954</start>
<end>2967</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering
%A Duan, Zhibin
%A Zhang, Hao
%A Wang, Chaojie
%A Wang, Zhengjue
%A Chen, Bo
%A Zhou, Mingyuan
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F duan-etal-2021-enslm
%X Natural language processing (NLP) often faces the problem of data diversity such as different domains, themes, styles, and so on. Therefore, a single language model (LM) is insufficient to learn all knowledge from diverse samples. To solve this problem, we firstly propose an autoencoding topic model with a mixture prior (mATM) to perform clustering for the data, where the clusters defined in semantic space describes the data diversity. Having obtained the clustering assignment for each sample, we develop the ensemble LM (EnsLM) with the technique of weight modulation. Specifically, EnsLM contains a backbone that is adjusted by a few modulated weights to fit for different sample clusters. As a result, the backbone learns the shared knowledge among all clusters while modulated weights extract the cluster-specific features. EnsLM can be trained jointly with mATM with a flexible LM backbone. We evaluate the effectiveness of both mATM and EnsLM on various tasks.
%R 10.18653/v1/2021.acl-long.230
%U https://aclanthology.org/2021.acl-long.230
%U https://doi.org/10.18653/v1/2021.acl-long.230
%P 2954-2967
Markdown (Informal)
[EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering](https://aclanthology.org/2021.acl-long.230) (Duan et al., ACL-IJCNLP 2021)
ACL
- Zhibin Duan, Hao Zhang, Chaojie Wang, Zhengjue Wang, Bo Chen, and Mingyuan Zhou. 2021. EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2954–2967, Online. Association for Computational Linguistics.