@inproceedings{thompson-etal-2019-hablex,
title = "{HABL}ex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation",
author = "Thompson, Brian and
Knowles, Rebecca and
Zhang, Xuan and
Khayrallah, Huda and
Duh, Kevin and
Koehn, Philipp",
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/D19-1142",
doi = "10.18653/v1/D19-1142",
pages = "1382--1387",
abstract = "Bilingual lexicons are valuable resources used by professional human translators. While these resources can be easily incorporated in statistical machine translation, it is unclear how to best do so in the neural framework. In this work, we present the HABLex dataset, designed to test methods for bilingual lexicon integration into neural machine translation. Our data consists of human generated alignments of words and phrases in machine translation test sets in three language pairs (Russian-English, Chinese-English, and Korean-English), resulting in clean bilingual lexicons which are well matched to the reference. We also present two simple baselines - constrained decoding and continued training - and an improvement to continued training to address overfitting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thompson-etal-2019-hablex">
<titleInfo>
<title>HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Knowles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huda</namePart>
<namePart type="family">Khayrallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</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>Bilingual lexicons are valuable resources used by professional human translators. While these resources can be easily incorporated in statistical machine translation, it is unclear how to best do so in the neural framework. In this work, we present the HABLex dataset, designed to test methods for bilingual lexicon integration into neural machine translation. Our data consists of human generated alignments of words and phrases in machine translation test sets in three language pairs (Russian-English, Chinese-English, and Korean-English), resulting in clean bilingual lexicons which are well matched to the reference. We also present two simple baselines - constrained decoding and continued training - and an improvement to continued training to address overfitting.</abstract>
<identifier type="citekey">thompson-etal-2019-hablex</identifier>
<identifier type="doi">10.18653/v1/D19-1142</identifier>
<location>
<url>https://aclanthology.org/D19-1142</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1382</start>
<end>1387</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation
%A Thompson, Brian
%A Knowles, Rebecca
%A Zhang, Xuan
%A Khayrallah, Huda
%A Duh, Kevin
%A Koehn, Philipp
%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 thompson-etal-2019-hablex
%X Bilingual lexicons are valuable resources used by professional human translators. While these resources can be easily incorporated in statistical machine translation, it is unclear how to best do so in the neural framework. In this work, we present the HABLex dataset, designed to test methods for bilingual lexicon integration into neural machine translation. Our data consists of human generated alignments of words and phrases in machine translation test sets in three language pairs (Russian-English, Chinese-English, and Korean-English), resulting in clean bilingual lexicons which are well matched to the reference. We also present two simple baselines - constrained decoding and continued training - and an improvement to continued training to address overfitting.
%R 10.18653/v1/D19-1142
%U https://aclanthology.org/D19-1142
%U https://doi.org/10.18653/v1/D19-1142
%P 1382-1387
Markdown (Informal)
[HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation](https://aclanthology.org/D19-1142) (Thompson et al., EMNLP-IJCNLP 2019)
ACL
- Brian Thompson, Rebecca Knowles, Xuan Zhang, Huda Khayrallah, Kevin Duh, and Philipp Koehn. 2019. HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation. 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 1382–1387, Hong Kong, China. Association for Computational Linguistics.