@inproceedings{richburg-etal-2020-evaluation,
title = "An Evaluation of Subword Segmentation Strategies for Neural Machine Translation of Morphologically Rich Languages",
author = "Richburg, Aquia and
Eskander, Ramy and
Muresan, Smaranda and
Carpuat, Marine",
editor = "Cunha, Rossana and
Shaikh, Samira and
Varis, Erika and
Georgi, Ryan and
Tsai, Alicia and
Anastasopoulos, Antonios and
Chandu, Khyathi Raghavi",
booktitle = "Proceedings of the Fourth Widening Natural Language Processing Workshop",
month = jul,
year = "2020",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.winlp-1.40/",
doi = "10.18653/v1/2020.winlp-1.40",
pages = "151--155",
abstract = "Byte-Pair Encoding (BPE) (Sennrich et al., 2016) has become a standard pre-processing step when building neural machine translation systems. However, it is not clear whether this is an optimal strategy in all settings. We conduct a controlled comparison of subword segmentation strategies for translating two low-resource morphologically rich languages (Swahili and Turkish) into English. We show that segmentations based on a unigram language model (Kudo, 2018) yield comparable BLEU and better recall for translating rare source words than BPE."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="richburg-etal-2020-evaluation">
<titleInfo>
<title>An Evaluation of Subword Segmentation Strategies for Neural Machine Translation of Morphologically Rich Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aquia</namePart>
<namePart type="family">Richburg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Widening Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rossana</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erika</namePart>
<namePart type="family">Varis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Georgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Byte-Pair Encoding (BPE) (Sennrich et al., 2016) has become a standard pre-processing step when building neural machine translation systems. However, it is not clear whether this is an optimal strategy in all settings. We conduct a controlled comparison of subword segmentation strategies for translating two low-resource morphologically rich languages (Swahili and Turkish) into English. We show that segmentations based on a unigram language model (Kudo, 2018) yield comparable BLEU and better recall for translating rare source words than BPE.</abstract>
<identifier type="citekey">richburg-etal-2020-evaluation</identifier>
<identifier type="doi">10.18653/v1/2020.winlp-1.40</identifier>
<location>
<url>https://aclanthology.org/2020.winlp-1.40/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>151</start>
<end>155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Evaluation of Subword Segmentation Strategies for Neural Machine Translation of Morphologically Rich Languages
%A Richburg, Aquia
%A Eskander, Ramy
%A Muresan, Smaranda
%A Carpuat, Marine
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Varis, Erika
%Y Georgi, Ryan
%Y Tsai, Alicia
%Y Anastasopoulos, Antonios
%Y Chandu, Khyathi Raghavi
%S Proceedings of the Fourth Widening Natural Language Processing Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F richburg-etal-2020-evaluation
%X Byte-Pair Encoding (BPE) (Sennrich et al., 2016) has become a standard pre-processing step when building neural machine translation systems. However, it is not clear whether this is an optimal strategy in all settings. We conduct a controlled comparison of subword segmentation strategies for translating two low-resource morphologically rich languages (Swahili and Turkish) into English. We show that segmentations based on a unigram language model (Kudo, 2018) yield comparable BLEU and better recall for translating rare source words than BPE.
%R 10.18653/v1/2020.winlp-1.40
%U https://aclanthology.org/2020.winlp-1.40/
%U https://doi.org/10.18653/v1/2020.winlp-1.40
%P 151-155
Markdown (Informal)
[An Evaluation of Subword Segmentation Strategies for Neural Machine Translation of Morphologically Rich Languages](https://aclanthology.org/2020.winlp-1.40/) (Richburg et al., WiNLP 2020)
ACL