@inproceedings{indurthi-etal-2022-language,
title = "Language Model Augmented Monotonic Attention for Simultaneous Translation",
author = "Indurthi, Sathish Reddy and
Zaidi, Mohd Abbas and
Lee, Beomseok and
Lakumarapu, Nikhil Kumar and
Kim, Sangha",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.3",
doi = "10.18653/v1/2022.naacl-main.3",
pages = "38--45",
abstract = "The state-of-the-art adaptive policies for Simultaneous Neural Machine Translation (SNMT) use monotonic attention to perform read/write decisions based on the partial source and target sequences. The lack of sufficient information might cause the monotonic attention to take poor read/write decisions, which in turn negatively affects the performance of the SNMT model. On the other hand, human translators make better read/write decisions since they can anticipate the immediate future words using linguistic information and domain knowledge. In this work, we propose a framework to aid monotonic attention with an external language model to improve its decisions. Experiments on MuST-C English-German and English-French speech-to-text translation tasks show the future information from the language model improves the state-of-the-art monotonic multi-head attention model further.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="indurthi-etal-2022-language">
<titleInfo>
<title>Language Model Augmented Monotonic Attention for Simultaneous Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sathish</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Indurthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohd</namePart>
<namePart type="given">Abbas</namePart>
<namePart type="family">Zaidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beomseok</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Lakumarapu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sangha</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The state-of-the-art adaptive policies for Simultaneous Neural Machine Translation (SNMT) use monotonic attention to perform read/write decisions based on the partial source and target sequences. The lack of sufficient information might cause the monotonic attention to take poor read/write decisions, which in turn negatively affects the performance of the SNMT model. On the other hand, human translators make better read/write decisions since they can anticipate the immediate future words using linguistic information and domain knowledge. In this work, we propose a framework to aid monotonic attention with an external language model to improve its decisions. Experiments on MuST-C English-German and English-French speech-to-text translation tasks show the future information from the language model improves the state-of-the-art monotonic multi-head attention model further.</abstract>
<identifier type="citekey">indurthi-etal-2022-language</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.3</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.3</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>38</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Model Augmented Monotonic Attention for Simultaneous Translation
%A Indurthi, Sathish Reddy
%A Zaidi, Mohd Abbas
%A Lee, Beomseok
%A Lakumarapu, Nikhil Kumar
%A Kim, Sangha
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F indurthi-etal-2022-language
%X The state-of-the-art adaptive policies for Simultaneous Neural Machine Translation (SNMT) use monotonic attention to perform read/write decisions based on the partial source and target sequences. The lack of sufficient information might cause the monotonic attention to take poor read/write decisions, which in turn negatively affects the performance of the SNMT model. On the other hand, human translators make better read/write decisions since they can anticipate the immediate future words using linguistic information and domain knowledge. In this work, we propose a framework to aid monotonic attention with an external language model to improve its decisions. Experiments on MuST-C English-German and English-French speech-to-text translation tasks show the future information from the language model improves the state-of-the-art monotonic multi-head attention model further.
%R 10.18653/v1/2022.naacl-main.3
%U https://aclanthology.org/2022.naacl-main.3
%U https://doi.org/10.18653/v1/2022.naacl-main.3
%P 38-45
Markdown (Informal)
[Language Model Augmented Monotonic Attention for Simultaneous Translation](https://aclanthology.org/2022.naacl-main.3) (Indurthi et al., NAACL 2022)
ACL
- Sathish Reddy Indurthi, Mohd Abbas Zaidi, Beomseok Lee, Nikhil Kumar Lakumarapu, and Sangha Kim. 2022. Language Model Augmented Monotonic Attention for Simultaneous Translation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 38–45, Seattle, United States. Association for Computational Linguistics.