@inproceedings{khwileh-etal-2017-identifying,
title = "Identifying Effective Translations for Cross-lingual {A}rabic-to-{E}nglish User-generated Speech Search",
author = "Khwileh, Ahmad and
Afli, Haithem and
Jones, Gareth and
Way, Andy",
editor = "Habash, Nizar and
Diab, Mona and
Darwish, Kareem and
El-Hajj, Wassim and
Al-Khalifa, Hend and
Bouamor, Houda and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Third {A}rabic Natural Language Processing Workshop",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1313",
doi = "10.18653/v1/W17-1313",
pages = "100--109",
abstract = "Cross Language Information Retrieval (CLIR) systems are a valuable tool to enable speakers of one language to search for content of interest expressed in a different language. A group for whom this is of particular interest is bilingual Arabic speakers who wish to search for English language content using information needs expressed in Arabic queries. A key challenge in CLIR is crossing the language barrier between the query and the documents. The most common approach to bridging this gap is automated query translation, which can be unreliable for vague or short queries. In this work, we examine the potential for improving CLIR effectiveness by predicting the translation effectiveness using Query Performance Prediction (QPP) techniques. We propose a novel QPP method to estimate the quality of translation for an Arabic-English Cross-lingual User-generated Speech Search (CLUGS) task. We present an empirical evaluation that demonstrates the quality of our method on alternative translation outputs extracted from an Arabic-to-English Machine Translation system developed for this task. Finally, we show how this framework can be integrated in CLUGS to find relevant translations for improved retrieval performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khwileh-etal-2017-identifying">
<titleInfo>
<title>Identifying Effective Translations for Cross-lingual Arabic-to-English User-generated Speech Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Khwileh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haithem</namePart>
<namePart type="family">Afli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gareth</namePart>
<namePart type="family">Jones</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Way</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">El-Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross Language Information Retrieval (CLIR) systems are a valuable tool to enable speakers of one language to search for content of interest expressed in a different language. A group for whom this is of particular interest is bilingual Arabic speakers who wish to search for English language content using information needs expressed in Arabic queries. A key challenge in CLIR is crossing the language barrier between the query and the documents. The most common approach to bridging this gap is automated query translation, which can be unreliable for vague or short queries. In this work, we examine the potential for improving CLIR effectiveness by predicting the translation effectiveness using Query Performance Prediction (QPP) techniques. We propose a novel QPP method to estimate the quality of translation for an Arabic-English Cross-lingual User-generated Speech Search (CLUGS) task. We present an empirical evaluation that demonstrates the quality of our method on alternative translation outputs extracted from an Arabic-to-English Machine Translation system developed for this task. Finally, we show how this framework can be integrated in CLUGS to find relevant translations for improved retrieval performance.</abstract>
<identifier type="citekey">khwileh-etal-2017-identifying</identifier>
<identifier type="doi">10.18653/v1/W17-1313</identifier>
<location>
<url>https://aclanthology.org/W17-1313</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>100</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Effective Translations for Cross-lingual Arabic-to-English User-generated Speech Search
%A Khwileh, Ahmad
%A Afli, Haithem
%A Jones, Gareth
%A Way, Andy
%Y Habash, Nizar
%Y Diab, Mona
%Y Darwish, Kareem
%Y El-Hajj, Wassim
%Y Al-Khalifa, Hend
%Y Bouamor, Houda
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Third Arabic Natural Language Processing Workshop
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F khwileh-etal-2017-identifying
%X Cross Language Information Retrieval (CLIR) systems are a valuable tool to enable speakers of one language to search for content of interest expressed in a different language. A group for whom this is of particular interest is bilingual Arabic speakers who wish to search for English language content using information needs expressed in Arabic queries. A key challenge in CLIR is crossing the language barrier between the query and the documents. The most common approach to bridging this gap is automated query translation, which can be unreliable for vague or short queries. In this work, we examine the potential for improving CLIR effectiveness by predicting the translation effectiveness using Query Performance Prediction (QPP) techniques. We propose a novel QPP method to estimate the quality of translation for an Arabic-English Cross-lingual User-generated Speech Search (CLUGS) task. We present an empirical evaluation that demonstrates the quality of our method on alternative translation outputs extracted from an Arabic-to-English Machine Translation system developed for this task. Finally, we show how this framework can be integrated in CLUGS to find relevant translations for improved retrieval performance.
%R 10.18653/v1/W17-1313
%U https://aclanthology.org/W17-1313
%U https://doi.org/10.18653/v1/W17-1313
%P 100-109
Markdown (Informal)
[Identifying Effective Translations for Cross-lingual Arabic-to-English User-generated Speech Search](https://aclanthology.org/W17-1313) (Khwileh et al., WANLP 2017)
ACL