@inproceedings{lignos-etal-2019-challenges,
title = "The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval",
author = "Lignos, Constantine and
Cohen, Daniel and
Lien, Yen-Chieh and
Mehta, Pratik and
Croft, W. Bruce and
Miller, Scott",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1353",
doi = "10.18653/v1/D19-1353",
pages = "3497--3502",
abstract = "When performing cross-language information retrieval (CLIR) for lower-resourced languages, a common approach is to retrieve over the output of machine translation (MT). However, there is no established guidance on how to optimize the resulting MT-IR system. In this paper, we examine the relationship between the performance of MT systems and both neural and term frequency-based IR models to identify how CLIR performance can be best predicted from MT quality. We explore performance at varying amounts of MT training data, byte pair encoding (BPE) merge operations, and across two IR collections and retrieval models. We find that the choice of IR collection can substantially affect the predictive power of MT tuning decisions and evaluation, potentially introducing dissociations between MT-only and overall CLIR performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lignos-etal-2019-challenges">
<titleInfo>
<title>The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yen-Chieh</namePart>
<namePart type="family">Lien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratik</namePart>
<namePart type="family">Mehta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">W</namePart>
<namePart type="given">Bruce</namePart>
<namePart type="family">Croft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When performing cross-language information retrieval (CLIR) for lower-resourced languages, a common approach is to retrieve over the output of machine translation (MT). However, there is no established guidance on how to optimize the resulting MT-IR system. In this paper, we examine the relationship between the performance of MT systems and both neural and term frequency-based IR models to identify how CLIR performance can be best predicted from MT quality. We explore performance at varying amounts of MT training data, byte pair encoding (BPE) merge operations, and across two IR collections and retrieval models. We find that the choice of IR collection can substantially affect the predictive power of MT tuning decisions and evaluation, potentially introducing dissociations between MT-only and overall CLIR performance.</abstract>
<identifier type="citekey">lignos-etal-2019-challenges</identifier>
<identifier type="doi">10.18653/v1/D19-1353</identifier>
<location>
<url>https://aclanthology.org/D19-1353</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>3497</start>
<end>3502</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval
%A Lignos, Constantine
%A Cohen, Daniel
%A Lien, Yen-Chieh
%A Mehta, Pratik
%A Croft, W. Bruce
%A Miller, Scott
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F lignos-etal-2019-challenges
%X When performing cross-language information retrieval (CLIR) for lower-resourced languages, a common approach is to retrieve over the output of machine translation (MT). However, there is no established guidance on how to optimize the resulting MT-IR system. In this paper, we examine the relationship between the performance of MT systems and both neural and term frequency-based IR models to identify how CLIR performance can be best predicted from MT quality. We explore performance at varying amounts of MT training data, byte pair encoding (BPE) merge operations, and across two IR collections and retrieval models. We find that the choice of IR collection can substantially affect the predictive power of MT tuning decisions and evaluation, potentially introducing dissociations between MT-only and overall CLIR performance.
%R 10.18653/v1/D19-1353
%U https://aclanthology.org/D19-1353
%U https://doi.org/10.18653/v1/D19-1353
%P 3497-3502
Markdown (Informal)
[The Challenges of Optimizing Machine Translation for Low Resource Cross-Language Information Retrieval](https://aclanthology.org/D19-1353) (Lignos et al., EMNLP-IJCNLP 2019)
ACL