@inproceedings{zenkel-etal-2020-end,
title = "End-to-End Neural Word Alignment Outperforms {GIZA}++",
author = "Zenkel, Thomas and
Wuebker, Joern and
DeNero, John",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.146/",
doi = "10.18653/v1/2020.acl-main.146",
pages = "1605--1617",
abstract = "Word alignment was once a core unsupervised learning task in natural language processing because of its essential role in training statistical machine translation (MT) models. Although unnecessary for training neural MT models, word alignment still plays an important role in interactive applications of neural machine translation, such as annotation transfer and lexicon injection. While statistical MT methods have been replaced by neural approaches with superior performance, the twenty-year-old GIZA++ toolkit remains a key component of state-of-the-art word alignment systems. Prior work on neural word alignment has only been able to outperform GIZA++ by using its output during training. We present the first end-to-end neural word alignment method that consistently outperforms GIZA++ on three data sets. Our approach repurposes a Transformer model trained for supervised translation to also serve as an unsupervised word alignment model in a manner that is tightly integrated and does not affect translation quality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zenkel-etal-2020-end">
<titleInfo>
<title>End-to-End Neural Word Alignment Outperforms GIZA++</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Zenkel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joern</namePart>
<namePart type="family">Wuebker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">DeNero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</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>Word alignment was once a core unsupervised learning task in natural language processing because of its essential role in training statistical machine translation (MT) models. Although unnecessary for training neural MT models, word alignment still plays an important role in interactive applications of neural machine translation, such as annotation transfer and lexicon injection. While statistical MT methods have been replaced by neural approaches with superior performance, the twenty-year-old GIZA++ toolkit remains a key component of state-of-the-art word alignment systems. Prior work on neural word alignment has only been able to outperform GIZA++ by using its output during training. We present the first end-to-end neural word alignment method that consistently outperforms GIZA++ on three data sets. Our approach repurposes a Transformer model trained for supervised translation to also serve as an unsupervised word alignment model in a manner that is tightly integrated and does not affect translation quality.</abstract>
<identifier type="citekey">zenkel-etal-2020-end</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.146</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.146/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>1605</start>
<end>1617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T End-to-End Neural Word Alignment Outperforms GIZA++
%A Zenkel, Thomas
%A Wuebker, Joern
%A DeNero, John
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F zenkel-etal-2020-end
%X Word alignment was once a core unsupervised learning task in natural language processing because of its essential role in training statistical machine translation (MT) models. Although unnecessary for training neural MT models, word alignment still plays an important role in interactive applications of neural machine translation, such as annotation transfer and lexicon injection. While statistical MT methods have been replaced by neural approaches with superior performance, the twenty-year-old GIZA++ toolkit remains a key component of state-of-the-art word alignment systems. Prior work on neural word alignment has only been able to outperform GIZA++ by using its output during training. We present the first end-to-end neural word alignment method that consistently outperforms GIZA++ on three data sets. Our approach repurposes a Transformer model trained for supervised translation to also serve as an unsupervised word alignment model in a manner that is tightly integrated and does not affect translation quality.
%R 10.18653/v1/2020.acl-main.146
%U https://aclanthology.org/2020.acl-main.146/
%U https://doi.org/10.18653/v1/2020.acl-main.146
%P 1605-1617
Markdown (Informal)
[End-to-End Neural Word Alignment Outperforms GIZA++](https://aclanthology.org/2020.acl-main.146/) (Zenkel et al., ACL 2020)
ACL
- Thomas Zenkel, Joern Wuebker, and John DeNero. 2020. End-to-End Neural Word Alignment Outperforms GIZA++. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1605–1617, Online. Association for Computational Linguistics.