@inproceedings{zhang-etal-2022-third,
title = "Third-Party Aligner for Neural Word Alignments",
author = "Zhang, Jinpeng and
Dong, Chuanqi and
Duan, Xiangyu and
Zhang, Yuqi and
Zhang, Min",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.228",
doi = "10.18653/v1/2022.findings-emnlp.228",
pages = "3134--3145",
abstract = "Word alignment is to find translationally equivalent words between source and target sentences. Previous work has demonstrated that self-training can achieve competitive word alignment results. In this paper, we propose to use word alignments generated by a third-party word aligner to supervise the neural word alignment training. Specifically, source word and target word of each word pair aligned by the third-party aligner are trained to be close neighbors to each other in the contextualized embedding space when fine-tuning a pre-trained cross-lingual language model. Experiments on the benchmarks of various language pairs show that our approach can surprisingly do self-correction over the third-party supervision by finding more accurate word alignments and deleting wrong word alignments, leading to better performance than various third-party word aligners, including the currently best one. When we integrate all supervisions from various third-party aligners, we achieve state-of-the-art word alignment performances, with averagely more than two points lower alignment error rates than the best third-party aligner. We released our code at \url{https://github.com/sdongchuanqi/Third-Party-Supervised-Aligner}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-third">
<titleInfo>
<title>Third-Party Aligner for Neural Word Alignments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinpeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuanqi</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word alignment is to find translationally equivalent words between source and target sentences. Previous work has demonstrated that self-training can achieve competitive word alignment results. In this paper, we propose to use word alignments generated by a third-party word aligner to supervise the neural word alignment training. Specifically, source word and target word of each word pair aligned by the third-party aligner are trained to be close neighbors to each other in the contextualized embedding space when fine-tuning a pre-trained cross-lingual language model. Experiments on the benchmarks of various language pairs show that our approach can surprisingly do self-correction over the third-party supervision by finding more accurate word alignments and deleting wrong word alignments, leading to better performance than various third-party word aligners, including the currently best one. When we integrate all supervisions from various third-party aligners, we achieve state-of-the-art word alignment performances, with averagely more than two points lower alignment error rates than the best third-party aligner. We released our code at https://github.com/sdongchuanqi/Third-Party-Supervised-Aligner.</abstract>
<identifier type="citekey">zhang-etal-2022-third</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.228</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.228</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3134</start>
<end>3145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Third-Party Aligner for Neural Word Alignments
%A Zhang, Jinpeng
%A Dong, Chuanqi
%A Duan, Xiangyu
%A Zhang, Yuqi
%A Zhang, Min
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhang-etal-2022-third
%X Word alignment is to find translationally equivalent words between source and target sentences. Previous work has demonstrated that self-training can achieve competitive word alignment results. In this paper, we propose to use word alignments generated by a third-party word aligner to supervise the neural word alignment training. Specifically, source word and target word of each word pair aligned by the third-party aligner are trained to be close neighbors to each other in the contextualized embedding space when fine-tuning a pre-trained cross-lingual language model. Experiments on the benchmarks of various language pairs show that our approach can surprisingly do self-correction over the third-party supervision by finding more accurate word alignments and deleting wrong word alignments, leading to better performance than various third-party word aligners, including the currently best one. When we integrate all supervisions from various third-party aligners, we achieve state-of-the-art word alignment performances, with averagely more than two points lower alignment error rates than the best third-party aligner. We released our code at https://github.com/sdongchuanqi/Third-Party-Supervised-Aligner.
%R 10.18653/v1/2022.findings-emnlp.228
%U https://aclanthology.org/2022.findings-emnlp.228
%U https://doi.org/10.18653/v1/2022.findings-emnlp.228
%P 3134-3145
Markdown (Informal)
[Third-Party Aligner for Neural Word Alignments](https://aclanthology.org/2022.findings-emnlp.228) (Zhang et al., Findings 2022)
ACL
- Jinpeng Zhang, Chuanqi Dong, Xiangyu Duan, Yuqi Zhang, and Min Zhang. 2022. Third-Party Aligner for Neural Word Alignments. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3134–3145, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.