@inproceedings{shi-etal-2019-retrofitting,
title = "Retrofitting Contextualized Word Embeddings with Paraphrases",
author = "Shi, Weijia and
Chen, Muhao and
Zhou, Pei and
Chang, Kai-Wei",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1113/",
doi = "10.18653/v1/D19-1113",
pages = "1198--1203",
abstract = "Contextualized word embeddings, such as ELMo, provide meaningful representations for words and their contexts. They have been shown to have a great impact on downstream applications. However, we observe that the contextualized embeddings of a word might change drastically when its contexts are paraphrased. As these embeddings are over-sensitive to the context, the downstream model may make different predictions when the input sentence is paraphrased. To address this issue, we propose a post-processing approach to retrofit the embedding with paraphrases. Our method learns an orthogonal transformation on the input space of the contextualized word embedding model, which seeks to minimize the variance of word representations on paraphrased contexts. Experiments show that the proposed method significantly improves ELMo on various sentence classification and inference tasks."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2019-retrofitting">
<titleInfo>
<title>Retrofitting Contextualized Word Embeddings with Paraphrases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weijia</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Contextualized word embeddings, such as ELMo, provide meaningful representations for words and their contexts. They have been shown to have a great impact on downstream applications. However, we observe that the contextualized embeddings of a word might change drastically when its contexts are paraphrased. As these embeddings are over-sensitive to the context, the downstream model may make different predictions when the input sentence is paraphrased. To address this issue, we propose a post-processing approach to retrofit the embedding with paraphrases. Our method learns an orthogonal transformation on the input space of the contextualized word embedding model, which seeks to minimize the variance of word representations on paraphrased contexts. Experiments show that the proposed method significantly improves ELMo on various sentence classification and inference tasks.</abstract>
<identifier type="citekey">shi-etal-2019-retrofitting</identifier>
<identifier type="doi">10.18653/v1/D19-1113</identifier>
<location>
<url>https://aclanthology.org/D19-1113/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1198</start>
<end>1203</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrofitting Contextualized Word Embeddings with Paraphrases
%A Shi, Weijia
%A Chen, Muhao
%A Zhou, Pei
%A Chang, Kai-Wei
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F shi-etal-2019-retrofitting
%X Contextualized word embeddings, such as ELMo, provide meaningful representations for words and their contexts. They have been shown to have a great impact on downstream applications. However, we observe that the contextualized embeddings of a word might change drastically when its contexts are paraphrased. As these embeddings are over-sensitive to the context, the downstream model may make different predictions when the input sentence is paraphrased. To address this issue, we propose a post-processing approach to retrofit the embedding with paraphrases. Our method learns an orthogonal transformation on the input space of the contextualized word embedding model, which seeks to minimize the variance of word representations on paraphrased contexts. Experiments show that the proposed method significantly improves ELMo on various sentence classification and inference tasks.
%R 10.18653/v1/D19-1113
%U https://aclanthology.org/D19-1113/
%U https://doi.org/10.18653/v1/D19-1113
%P 1198-1203
Markdown (Informal)
[Retrofitting Contextualized Word Embeddings with Paraphrases](https://aclanthology.org/D19-1113/) (Shi et al., EMNLP-IJCNLP 2019)
ACL
- Weijia Shi, Muhao Chen, Pei Zhou, and Kai-Wei Chang. 2019. Retrofitting Contextualized Word Embeddings with Paraphrases. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1198–1203, Hong Kong, China. Association for Computational Linguistics.