@inproceedings{ham-kim-2021-semantic-alignment,
title = "Semantic Alignment with Calibrated Similarity for Multilingual Sentence Embedding",
author = "Ham, Jiyeon and
Kim, Eun-Sol",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.153",
doi = "10.18653/v1/2021.findings-emnlp.153",
pages = "1781--1791",
abstract = "Measuring the similarity score between a pair of sentences in different languages is the essential requisite for multilingual sentence embedding methods. Predicting the similarity score consists of two sub-tasks, which are monolingual similarity evaluation and multilingual sentence retrieval. However, conventional methods have mainly tackled only one of the sub-tasks and therefore showed biased performances. In this paper, we suggest a novel and strong method for multilingual sentence embedding, which shows performance improvement on both sub-tasks, consequently resulting in robust predictions of multilingual similarity scores. The suggested method consists of two parts: to learn semantic similarity of sentences in the pivot language and then to extend the learned semantic structure to different languages. To align semantic structures across different languages, we introduce a teacher-student network. The teacher network distills the knowledge of the pivot language to different languages of the student network. During the distillation, the parameters of the teacher network are updated with the slow-moving average. Together with the distillation and the parameter updating, the semantic structure of the student network can be directly aligned across different languages while preserving the ability to measure the semantic similarity. Thus, the multilingual training method drives performance improvement on multilingual similarity evaluation. The suggested model achieves the state-of-the-art performance on extended STS 2017 multilingual similarity evaluation as well as two sub-tasks, which are extended STS 2017 monolingual similarity evaluation and Tatoeba multilingual retrieval in 14 languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ham-kim-2021-semantic-alignment">
<titleInfo>
<title>Semantic Alignment with Calibrated Similarity for Multilingual Sentence Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiyeon</namePart>
<namePart type="family">Ham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eun-Sol</namePart>
<namePart type="family">Kim</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>Findings of the Association for Computational Linguistics: EMNLP 2021</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">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Measuring the similarity score between a pair of sentences in different languages is the essential requisite for multilingual sentence embedding methods. Predicting the similarity score consists of two sub-tasks, which are monolingual similarity evaluation and multilingual sentence retrieval. However, conventional methods have mainly tackled only one of the sub-tasks and therefore showed biased performances. In this paper, we suggest a novel and strong method for multilingual sentence embedding, which shows performance improvement on both sub-tasks, consequently resulting in robust predictions of multilingual similarity scores. The suggested method consists of two parts: to learn semantic similarity of sentences in the pivot language and then to extend the learned semantic structure to different languages. To align semantic structures across different languages, we introduce a teacher-student network. The teacher network distills the knowledge of the pivot language to different languages of the student network. During the distillation, the parameters of the teacher network are updated with the slow-moving average. Together with the distillation and the parameter updating, the semantic structure of the student network can be directly aligned across different languages while preserving the ability to measure the semantic similarity. Thus, the multilingual training method drives performance improvement on multilingual similarity evaluation. The suggested model achieves the state-of-the-art performance on extended STS 2017 multilingual similarity evaluation as well as two sub-tasks, which are extended STS 2017 monolingual similarity evaluation and Tatoeba multilingual retrieval in 14 languages.</abstract>
<identifier type="citekey">ham-kim-2021-semantic-alignment</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.153</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.153</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1781</start>
<end>1791</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Alignment with Calibrated Similarity for Multilingual Sentence Embedding
%A Ham, Jiyeon
%A Kim, Eun-Sol
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F ham-kim-2021-semantic-alignment
%X Measuring the similarity score between a pair of sentences in different languages is the essential requisite for multilingual sentence embedding methods. Predicting the similarity score consists of two sub-tasks, which are monolingual similarity evaluation and multilingual sentence retrieval. However, conventional methods have mainly tackled only one of the sub-tasks and therefore showed biased performances. In this paper, we suggest a novel and strong method for multilingual sentence embedding, which shows performance improvement on both sub-tasks, consequently resulting in robust predictions of multilingual similarity scores. The suggested method consists of two parts: to learn semantic similarity of sentences in the pivot language and then to extend the learned semantic structure to different languages. To align semantic structures across different languages, we introduce a teacher-student network. The teacher network distills the knowledge of the pivot language to different languages of the student network. During the distillation, the parameters of the teacher network are updated with the slow-moving average. Together with the distillation and the parameter updating, the semantic structure of the student network can be directly aligned across different languages while preserving the ability to measure the semantic similarity. Thus, the multilingual training method drives performance improvement on multilingual similarity evaluation. The suggested model achieves the state-of-the-art performance on extended STS 2017 multilingual similarity evaluation as well as two sub-tasks, which are extended STS 2017 monolingual similarity evaluation and Tatoeba multilingual retrieval in 14 languages.
%R 10.18653/v1/2021.findings-emnlp.153
%U https://aclanthology.org/2021.findings-emnlp.153
%U https://doi.org/10.18653/v1/2021.findings-emnlp.153
%P 1781-1791
Markdown (Informal)
[Semantic Alignment with Calibrated Similarity for Multilingual Sentence Embedding](https://aclanthology.org/2021.findings-emnlp.153) (Ham & Kim, Findings 2021)
ACL