@inproceedings{wang-etal-2021-phrase,
title = "Phrase-{BERT}: Improved Phrase Embeddings from {BERT} with an Application to Corpus Exploration",
author = "Wang, Shufan and
Thompson, Laure and
Iyyer, Mohit",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.846",
doi = "10.18653/v1/2021.emnlp-main.846",
pages = "10837--10851",
abstract = "Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness. In this paper, we propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings. Our approach (Phrase-BERT) relies on a dataset of diverse phrasal paraphrases, which is automatically generated using a paraphrase generation model, as well as a large-scale dataset of phrases in context mined from the Books3 corpus. Phrase-BERT outperforms baselines across a variety of phrase-level similarity tasks, while also demonstrating increased lexical diversity between nearest neighbors in the vector space. Finally, as a case study, we show that Phrase-BERT embeddings can be easily integrated with a simple autoencoder to build a phrase-based neural topic model that interprets topics as mixtures of words and phrases by performing a nearest neighbor search in the embedding space. Crowdsourced evaluations demonstrate that this phrase-based topic model produces more coherent and meaningful topics than baseline word and phrase-level topic models, further validating the utility of Phrase-BERT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-phrase">
<titleInfo>
<title>Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shufan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laure</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Iyyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness. In this paper, we propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings. Our approach (Phrase-BERT) relies on a dataset of diverse phrasal paraphrases, which is automatically generated using a paraphrase generation model, as well as a large-scale dataset of phrases in context mined from the Books3 corpus. Phrase-BERT outperforms baselines across a variety of phrase-level similarity tasks, while also demonstrating increased lexical diversity between nearest neighbors in the vector space. Finally, as a case study, we show that Phrase-BERT embeddings can be easily integrated with a simple autoencoder to build a phrase-based neural topic model that interprets topics as mixtures of words and phrases by performing a nearest neighbor search in the embedding space. Crowdsourced evaluations demonstrate that this phrase-based topic model produces more coherent and meaningful topics than baseline word and phrase-level topic models, further validating the utility of Phrase-BERT.</abstract>
<identifier type="citekey">wang-etal-2021-phrase</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.846</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.846</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>10837</start>
<end>10851</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration
%A Wang, Shufan
%A Thompson, Laure
%A Iyyer, Mohit
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F wang-etal-2021-phrase
%X Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness. In this paper, we propose a contrastive fine-tuning objective that enables BERT to produce more powerful phrase embeddings. Our approach (Phrase-BERT) relies on a dataset of diverse phrasal paraphrases, which is automatically generated using a paraphrase generation model, as well as a large-scale dataset of phrases in context mined from the Books3 corpus. Phrase-BERT outperforms baselines across a variety of phrase-level similarity tasks, while also demonstrating increased lexical diversity between nearest neighbors in the vector space. Finally, as a case study, we show that Phrase-BERT embeddings can be easily integrated with a simple autoencoder to build a phrase-based neural topic model that interprets topics as mixtures of words and phrases by performing a nearest neighbor search in the embedding space. Crowdsourced evaluations demonstrate that this phrase-based topic model produces more coherent and meaningful topics than baseline word and phrase-level topic models, further validating the utility of Phrase-BERT.
%R 10.18653/v1/2021.emnlp-main.846
%U https://aclanthology.org/2021.emnlp-main.846
%U https://doi.org/10.18653/v1/2021.emnlp-main.846
%P 10837-10851
Markdown (Informal)
[Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration](https://aclanthology.org/2021.emnlp-main.846) (Wang et al., EMNLP 2021)
ACL