@inproceedings{kunchukuttan-bhattacharyya-2017-learning,
title = "Learning variable length units for {SMT} between related languages via Byte Pair Encoding",
author = "Kunchukuttan, Anoop and
Bhattacharyya, Pushpak",
editor = "Faruqui, Manaal and
Schuetze, Hinrich and
Trancoso, Isabel and
Yaghoobzadeh, Yadollah",
booktitle = "Proceedings of the First Workshop on Subword and Character Level Models in {NLP}",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-4102",
doi = "10.18653/v1/W17-4102",
pages = "14--24",
abstract = "We explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are currently the best performing basic units for this translation task. BPE identifies the most frequent character sequences as basic units, while orthographic syllables are linguistically motivated pseudo-syllables. We show that BPE units modestly outperform orthographic syllables as units of translation, showing up to 11{\%} increase in BLEU score. While orthographic syllables can be used only for languages whose writing systems use vowel representations, BPE is writing system independent and we show that BPE outperforms other units for non-vowel writing systems too. Our results are supported by extensive experimentation spanning multiple language families and writing systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kunchukuttan-bhattacharyya-2017-learning">
<titleInfo>
<title>Learning variable length units for SMT between related languages via Byte Pair Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Subword and Character Level Models in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manaal</namePart>
<namePart type="family">Faruqui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schuetze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Trancoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadollah</namePart>
<namePart type="family">Yaghoobzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are currently the best performing basic units for this translation task. BPE identifies the most frequent character sequences as basic units, while orthographic syllables are linguistically motivated pseudo-syllables. We show that BPE units modestly outperform orthographic syllables as units of translation, showing up to 11% increase in BLEU score. While orthographic syllables can be used only for languages whose writing systems use vowel representations, BPE is writing system independent and we show that BPE outperforms other units for non-vowel writing systems too. Our results are supported by extensive experimentation spanning multiple language families and writing systems.</abstract>
<identifier type="citekey">kunchukuttan-bhattacharyya-2017-learning</identifier>
<identifier type="doi">10.18653/v1/W17-4102</identifier>
<location>
<url>https://aclanthology.org/W17-4102</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>14</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning variable length units for SMT between related languages via Byte Pair Encoding
%A Kunchukuttan, Anoop
%A Bhattacharyya, Pushpak
%Y Faruqui, Manaal
%Y Schuetze, Hinrich
%Y Trancoso, Isabel
%Y Yaghoobzadeh, Yadollah
%S Proceedings of the First Workshop on Subword and Character Level Models in NLP
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F kunchukuttan-bhattacharyya-2017-learning
%X We explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are currently the best performing basic units for this translation task. BPE identifies the most frequent character sequences as basic units, while orthographic syllables are linguistically motivated pseudo-syllables. We show that BPE units modestly outperform orthographic syllables as units of translation, showing up to 11% increase in BLEU score. While orthographic syllables can be used only for languages whose writing systems use vowel representations, BPE is writing system independent and we show that BPE outperforms other units for non-vowel writing systems too. Our results are supported by extensive experimentation spanning multiple language families and writing systems.
%R 10.18653/v1/W17-4102
%U https://aclanthology.org/W17-4102
%U https://doi.org/10.18653/v1/W17-4102
%P 14-24
Markdown (Informal)
[Learning variable length units for SMT between related languages via Byte Pair Encoding](https://aclanthology.org/W17-4102) (Kunchukuttan & Bhattacharyya, SCLeM 2017)
ACL