@inproceedings{lewis-etal-2020-neural,
title = "Neural Transduction for Multilingual Lexical Translation",
author = "Lewis, Dylan and
Wu, Winston and
McCarthy, Arya D. and
Yarowsky, David",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.387",
doi = "10.18653/v1/2020.coling-main.387",
pages = "4373--4384",
abstract = "We present a method for completing multilingual translation dictionaries. Our probabilistic approach can synthesize new word forms, allowing it to operate in settings where correct translations have not been observed in text (cf. cross-lingual embeddings). In addition, we propose an approximate Maximum Mutual Information (MMI) decoding objective to further improve performance in both many-to-one and one-to-one word level translation tasks where we use either multiple input languages for a single target language or more typical single language pair translation. The model is trained in a many-to-many setting, where it can leverage information from related languages to predict words in each of its many target languages. We focus on 6 languages: French, Spanish, Italian, Portuguese, Romanian, and Turkish. When indirect multilingual information is available, ensembling with mixture-of-experts as well as incorporating related languages leads to a 27{\%} relative improvement in whole-word accuracy of predictions over a single-source baseline. To seed the completion when multilingual data is unavailable, it is better to decode with an MMI objective.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lewis-etal-2020-neural">
<titleInfo>
<title>Neural Transduction for Multilingual Lexical Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dylan</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Winston</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arya</namePart>
<namePart type="given">D</namePart>
<namePart type="family">McCarthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Yarowsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a method for completing multilingual translation dictionaries. Our probabilistic approach can synthesize new word forms, allowing it to operate in settings where correct translations have not been observed in text (cf. cross-lingual embeddings). In addition, we propose an approximate Maximum Mutual Information (MMI) decoding objective to further improve performance in both many-to-one and one-to-one word level translation tasks where we use either multiple input languages for a single target language or more typical single language pair translation. The model is trained in a many-to-many setting, where it can leverage information from related languages to predict words in each of its many target languages. We focus on 6 languages: French, Spanish, Italian, Portuguese, Romanian, and Turkish. When indirect multilingual information is available, ensembling with mixture-of-experts as well as incorporating related languages leads to a 27% relative improvement in whole-word accuracy of predictions over a single-source baseline. To seed the completion when multilingual data is unavailable, it is better to decode with an MMI objective.</abstract>
<identifier type="citekey">lewis-etal-2020-neural</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.387</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.387</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4373</start>
<end>4384</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Transduction for Multilingual Lexical Translation
%A Lewis, Dylan
%A Wu, Winston
%A McCarthy, Arya D.
%A Yarowsky, David
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F lewis-etal-2020-neural
%X We present a method for completing multilingual translation dictionaries. Our probabilistic approach can synthesize new word forms, allowing it to operate in settings where correct translations have not been observed in text (cf. cross-lingual embeddings). In addition, we propose an approximate Maximum Mutual Information (MMI) decoding objective to further improve performance in both many-to-one and one-to-one word level translation tasks where we use either multiple input languages for a single target language or more typical single language pair translation. The model is trained in a many-to-many setting, where it can leverage information from related languages to predict words in each of its many target languages. We focus on 6 languages: French, Spanish, Italian, Portuguese, Romanian, and Turkish. When indirect multilingual information is available, ensembling with mixture-of-experts as well as incorporating related languages leads to a 27% relative improvement in whole-word accuracy of predictions over a single-source baseline. To seed the completion when multilingual data is unavailable, it is better to decode with an MMI objective.
%R 10.18653/v1/2020.coling-main.387
%U https://aclanthology.org/2020.coling-main.387
%U https://doi.org/10.18653/v1/2020.coling-main.387
%P 4373-4384
Markdown (Informal)
[Neural Transduction for Multilingual Lexical Translation](https://aclanthology.org/2020.coling-main.387) (Lewis et al., COLING 2020)
ACL
- Dylan Lewis, Winston Wu, Arya D. McCarthy, and David Yarowsky. 2020. Neural Transduction for Multilingual Lexical Translation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4373–4384, Barcelona, Spain (Online). International Committee on Computational Linguistics.