@inproceedings{gashaw-shashirekha-2019-language,
title = "Language Modelling with {NMT} Query Translation for {A}mharic-{A}rabic Cross-Language Information Retrieval",
author = "Gashaw, Ibrahim and
Shashirekha, H.l",
editor = "Sharma, Dipti Misra and
Bhattacharya, Pushpak",
booktitle = "Proceedings of the 16th International Conference on Natural Language Processing",
month = dec,
year = "2019",
address = "International Institute of Information Technology, Hyderabad, India",
publisher = "NLP Association of India",
url = "https://aclanthology.org/2019.icon-1.7",
pages = "56--64",
abstract = "This paper describes our first experiment on Neural Machine Translation (NMT) based query translation for Amharic-Arabic Cross-Language Information Retrieval (CLIR) task to retrieve relevant documents from Amharic and Arabic text collections in response to a query expressed in the Amharic language. We used a pre-trained NMT model to map a query in the source language into an equivalent query in the target language. The relevant documents are then retrieved using a Language Modeling (LM) based retrieval algorithm. Experiments are conducted on four conventional IR models, namely Uni-gram and Bi-gram LM, Probabilistic model, and Vector Space Model (VSM). The results obtained illustrate that the proposed Uni-gram LM outperforms all other models for both Amharic and Arabic language document collections.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gashaw-shashirekha-2019-language">
<titleInfo>
<title>Language Modelling with NMT Query Translation for Amharic-Arabic Cross-Language Information Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Gashaw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">H.l</namePart>
<namePart type="family">Shashirekha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India</publisher>
<place>
<placeTerm type="text">International Institute of Information Technology, Hyderabad, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our first experiment on Neural Machine Translation (NMT) based query translation for Amharic-Arabic Cross-Language Information Retrieval (CLIR) task to retrieve relevant documents from Amharic and Arabic text collections in response to a query expressed in the Amharic language. We used a pre-trained NMT model to map a query in the source language into an equivalent query in the target language. The relevant documents are then retrieved using a Language Modeling (LM) based retrieval algorithm. Experiments are conducted on four conventional IR models, namely Uni-gram and Bi-gram LM, Probabilistic model, and Vector Space Model (VSM). The results obtained illustrate that the proposed Uni-gram LM outperforms all other models for both Amharic and Arabic language document collections.</abstract>
<identifier type="citekey">gashaw-shashirekha-2019-language</identifier>
<location>
<url>https://aclanthology.org/2019.icon-1.7</url>
</location>
<part>
<date>2019-12</date>
<extent unit="page">
<start>56</start>
<end>64</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Modelling with NMT Query Translation for Amharic-Arabic Cross-Language Information Retrieval
%A Gashaw, Ibrahim
%A Shashirekha, H.l
%Y Sharma, Dipti Misra
%Y Bhattacharya, Pushpak
%S Proceedings of the 16th International Conference on Natural Language Processing
%D 2019
%8 December
%I NLP Association of India
%C International Institute of Information Technology, Hyderabad, India
%F gashaw-shashirekha-2019-language
%X This paper describes our first experiment on Neural Machine Translation (NMT) based query translation for Amharic-Arabic Cross-Language Information Retrieval (CLIR) task to retrieve relevant documents from Amharic and Arabic text collections in response to a query expressed in the Amharic language. We used a pre-trained NMT model to map a query in the source language into an equivalent query in the target language. The relevant documents are then retrieved using a Language Modeling (LM) based retrieval algorithm. Experiments are conducted on four conventional IR models, namely Uni-gram and Bi-gram LM, Probabilistic model, and Vector Space Model (VSM). The results obtained illustrate that the proposed Uni-gram LM outperforms all other models for both Amharic and Arabic language document collections.
%U https://aclanthology.org/2019.icon-1.7
%P 56-64
Markdown (Informal)
[Language Modelling with NMT Query Translation for Amharic-Arabic Cross-Language Information Retrieval](https://aclanthology.org/2019.icon-1.7) (Gashaw & Shashirekha, ICON 2019)
ACL