@article{irvine-callison-burch-2017-comprehensive,
title = "A Comprehensive Analysis of Bilingual Lexicon Induction",
author = "Irvine, Ann and
Callison-Burch, Chris",
journal = "Computational Linguistics",
volume = "43",
number = "2",
month = jun,
year = "2017",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/J17-2001",
doi = "10.1162/COLI_a_00284",
pages = "273--310",
abstract = "Bilingual lexicon induction is the task of inducing word translations from monolingual corpora in two languages. In this article we present the most comprehensive analysis of bilingual lexicon induction to date. We present experiments on a wide range of languages and data sizes. We examine translation into English from 25 foreign languages: Albanian, Azeri, Bengali, Bosnian, Bulgarian, Cebuano, Gujarati, Hindi, Hungarian, Indonesian, Latvian, Nepali, Romanian, Serbian, Slovak, Somali, Spanish, Swedish, Tamil, Telugu, Turkish, Ukrainian, Uzbek, Vietnamese, and Welsh. We analyze the behavior of bilingual lexicon induction on low-frequency words, rather than testing solely on high-frequency words, as previous research has done. Low-frequency words are more relevant to statistical machine translation, where systems typically lack translations of rare words that fall outside of their training data. We systematically explore a wide range of features and phenomena that affect the quality of the translations discovered by bilingual lexicon induction. We provide illustrative examples of the highest ranking translations for orthogonal signals of translation equivalence like contextual similarity and temporal similarity. We analyze the effects of frequency and burstiness, and the sizes of the seed bilingual dictionaries and the monolingual training corpora. Additionally, we introduce a novel discriminative approach to bilingual lexicon induction. Our discriminative model is capable of combining a wide variety of features that individually provide only weak indications of translation equivalence. When feature weights are discriminatively set, these signals produce dramatically higher translation quality than previous approaches that combined signals in an unsupervised fashion (e.g., using minimum reciprocal rank). We also directly compare our model{'}s performance against a sophisticated generative approach, the matching canonical correlation analysis (MCCA) algorithm used by Haghighi et al. (2008). Our algorithm achieves an accuracy of 42{\%} versus MCCA{'}s 15{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="irvine-callison-burch-2017-comprehensive">
<titleInfo>
<title>A Comprehensive Analysis of Bilingual Lexicon Induction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Irvine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Callison-Burch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Bilingual lexicon induction is the task of inducing word translations from monolingual corpora in two languages. In this article we present the most comprehensive analysis of bilingual lexicon induction to date. We present experiments on a wide range of languages and data sizes. We examine translation into English from 25 foreign languages: Albanian, Azeri, Bengali, Bosnian, Bulgarian, Cebuano, Gujarati, Hindi, Hungarian, Indonesian, Latvian, Nepali, Romanian, Serbian, Slovak, Somali, Spanish, Swedish, Tamil, Telugu, Turkish, Ukrainian, Uzbek, Vietnamese, and Welsh. We analyze the behavior of bilingual lexicon induction on low-frequency words, rather than testing solely on high-frequency words, as previous research has done. Low-frequency words are more relevant to statistical machine translation, where systems typically lack translations of rare words that fall outside of their training data. We systematically explore a wide range of features and phenomena that affect the quality of the translations discovered by bilingual lexicon induction. We provide illustrative examples of the highest ranking translations for orthogonal signals of translation equivalence like contextual similarity and temporal similarity. We analyze the effects of frequency and burstiness, and the sizes of the seed bilingual dictionaries and the monolingual training corpora. Additionally, we introduce a novel discriminative approach to bilingual lexicon induction. Our discriminative model is capable of combining a wide variety of features that individually provide only weak indications of translation equivalence. When feature weights are discriminatively set, these signals produce dramatically higher translation quality than previous approaches that combined signals in an unsupervised fashion (e.g., using minimum reciprocal rank). We also directly compare our model’s performance against a sophisticated generative approach, the matching canonical correlation analysis (MCCA) algorithm used by Haghighi et al. (2008). Our algorithm achieves an accuracy of 42% versus MCCA’s 15%.</abstract>
<identifier type="citekey">irvine-callison-burch-2017-comprehensive</identifier>
<identifier type="doi">10.1162/COLI_a_00284</identifier>
<location>
<url>https://aclanthology.org/J17-2001</url>
</location>
<part>
<date>2017-06</date>
<detail type="volume"><number>43</number></detail>
<detail type="issue"><number>2</number></detail>
<extent unit="page">
<start>273</start>
<end>310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T A Comprehensive Analysis of Bilingual Lexicon Induction
%A Irvine, Ann
%A Callison-Burch, Chris
%J Computational Linguistics
%D 2017
%8 June
%V 43
%N 2
%I MIT Press
%C Cambridge, MA
%F irvine-callison-burch-2017-comprehensive
%X Bilingual lexicon induction is the task of inducing word translations from monolingual corpora in two languages. In this article we present the most comprehensive analysis of bilingual lexicon induction to date. We present experiments on a wide range of languages and data sizes. We examine translation into English from 25 foreign languages: Albanian, Azeri, Bengali, Bosnian, Bulgarian, Cebuano, Gujarati, Hindi, Hungarian, Indonesian, Latvian, Nepali, Romanian, Serbian, Slovak, Somali, Spanish, Swedish, Tamil, Telugu, Turkish, Ukrainian, Uzbek, Vietnamese, and Welsh. We analyze the behavior of bilingual lexicon induction on low-frequency words, rather than testing solely on high-frequency words, as previous research has done. Low-frequency words are more relevant to statistical machine translation, where systems typically lack translations of rare words that fall outside of their training data. We systematically explore a wide range of features and phenomena that affect the quality of the translations discovered by bilingual lexicon induction. We provide illustrative examples of the highest ranking translations for orthogonal signals of translation equivalence like contextual similarity and temporal similarity. We analyze the effects of frequency and burstiness, and the sizes of the seed bilingual dictionaries and the monolingual training corpora. Additionally, we introduce a novel discriminative approach to bilingual lexicon induction. Our discriminative model is capable of combining a wide variety of features that individually provide only weak indications of translation equivalence. When feature weights are discriminatively set, these signals produce dramatically higher translation quality than previous approaches that combined signals in an unsupervised fashion (e.g., using minimum reciprocal rank). We also directly compare our model’s performance against a sophisticated generative approach, the matching canonical correlation analysis (MCCA) algorithm used by Haghighi et al. (2008). Our algorithm achieves an accuracy of 42% versus MCCA’s 15%.
%R 10.1162/COLI_a_00284
%U https://aclanthology.org/J17-2001
%U https://doi.org/10.1162/COLI_a_00284
%P 273-310
Markdown (Informal)
[A Comprehensive Analysis of Bilingual Lexicon Induction](https://aclanthology.org/J17-2001) (Irvine & Callison-Burch, CL 2017)
ACL