@inproceedings{mahesh-etal-2016-using,
title = "Using Bilingual Segments in Generating Word-to-word Translations",
author = "Mahesh, Kavitha and
Pereira Lopes, Gabriel and
Gomes, Lu{\'\i}s",
editor = "Lambert, Patrik and
Babych, Bogdan and
Eberle, Kurt and
Banchs, Rafael E. and
Rapp, Reinhard and
Costa-juss{\`a}, Marta R.",
booktitle = "Proceedings of the Sixth Workshop on Hybrid Approaches to Translation ({H}y{T}ra6)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4508",
pages = "61--71",
abstract = "We defend that bilingual lexicons automatically extracted from parallel corpora, whose entries have been meanwhile validated by linguists and classified as correct or incorrect, should constitute a specific parallel corpora. And, in this paper, we propose to use word-to-word translations to learn morph-units (comprising of bilingual stems and suffixes) from those bilingual lexicons for two language pairs L1-L2 and L1-L3 to induce a bilingual lexicon for the language pair L2-L3, apart from also learning morph-units for this other language pair. The applicability of bilingual morph-units in L1-L2 and L1-L3 is examined from the perspective of pivot-based lexicon induction for language pair L2-L3 with L1 as bridge. While the lexicon is derived by transitivity, the correspondences are identified based on previously learnt bilingual stems and suffixes rather than surface translation forms. The induced pairs are validated using a binary classifier trained on morphological and similarity-based features using an existing, automatically acquired, manually validated bilingual translation lexicon for language pair L2-L3. In this paper, we discuss the use of English (EN)-French (FR) and English (EN)-Portuguese (PT) lexicon of word-to-word translations in generating word-to-word translations for the language pair FR-PT with EN as pivot language. Generated translations are filtered out first using an SVM-based FR-PT classifier and then are manually validated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahesh-etal-2016-using">
<titleInfo>
<title>Using Bilingual Segments in Generating Word-to-word Translations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kavitha</namePart>
<namePart type="family">Mahesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Pereira Lopes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luís</namePart>
<namePart type="family">Gomes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrik</namePart>
<namePart type="family">Lambert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Babych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kurt</namePart>
<namePart type="family">Eberle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Banchs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We defend that bilingual lexicons automatically extracted from parallel corpora, whose entries have been meanwhile validated by linguists and classified as correct or incorrect, should constitute a specific parallel corpora. And, in this paper, we propose to use word-to-word translations to learn morph-units (comprising of bilingual stems and suffixes) from those bilingual lexicons for two language pairs L1-L2 and L1-L3 to induce a bilingual lexicon for the language pair L2-L3, apart from also learning morph-units for this other language pair. The applicability of bilingual morph-units in L1-L2 and L1-L3 is examined from the perspective of pivot-based lexicon induction for language pair L2-L3 with L1 as bridge. While the lexicon is derived by transitivity, the correspondences are identified based on previously learnt bilingual stems and suffixes rather than surface translation forms. The induced pairs are validated using a binary classifier trained on morphological and similarity-based features using an existing, automatically acquired, manually validated bilingual translation lexicon for language pair L2-L3. In this paper, we discuss the use of English (EN)-French (FR) and English (EN)-Portuguese (PT) lexicon of word-to-word translations in generating word-to-word translations for the language pair FR-PT with EN as pivot language. Generated translations are filtered out first using an SVM-based FR-PT classifier and then are manually validated.</abstract>
<identifier type="citekey">mahesh-etal-2016-using</identifier>
<location>
<url>https://aclanthology.org/W16-4508</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>61</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Bilingual Segments in Generating Word-to-word Translations
%A Mahesh, Kavitha
%A Pereira Lopes, Gabriel
%A Gomes, Luís
%Y Lambert, Patrik
%Y Babych, Bogdan
%Y Eberle, Kurt
%Y Banchs, Rafael E.
%Y Rapp, Reinhard
%Y Costa-jussà, Marta R.
%S Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F mahesh-etal-2016-using
%X We defend that bilingual lexicons automatically extracted from parallel corpora, whose entries have been meanwhile validated by linguists and classified as correct or incorrect, should constitute a specific parallel corpora. And, in this paper, we propose to use word-to-word translations to learn morph-units (comprising of bilingual stems and suffixes) from those bilingual lexicons for two language pairs L1-L2 and L1-L3 to induce a bilingual lexicon for the language pair L2-L3, apart from also learning morph-units for this other language pair. The applicability of bilingual morph-units in L1-L2 and L1-L3 is examined from the perspective of pivot-based lexicon induction for language pair L2-L3 with L1 as bridge. While the lexicon is derived by transitivity, the correspondences are identified based on previously learnt bilingual stems and suffixes rather than surface translation forms. The induced pairs are validated using a binary classifier trained on morphological and similarity-based features using an existing, automatically acquired, manually validated bilingual translation lexicon for language pair L2-L3. In this paper, we discuss the use of English (EN)-French (FR) and English (EN)-Portuguese (PT) lexicon of word-to-word translations in generating word-to-word translations for the language pair FR-PT with EN as pivot language. Generated translations are filtered out first using an SVM-based FR-PT classifier and then are manually validated.
%U https://aclanthology.org/W16-4508
%P 61-71
Markdown (Informal)
[Using Bilingual Segments in Generating Word-to-word Translations](https://aclanthology.org/W16-4508) (Mahesh et al., HyTra 2016)
ACL