@inproceedings{haq-etal-2024-indicirsuite,
title = "{I}ndic{IRS}uite: Multilingual Dataset and Neural Information Models for {I}ndian Languages",
author = "Haq, Saiful and
Sharma, Ashutosh and
Khattab, Omar and
Chhaya, Niyati and
Bhattacharyya, Pushpak",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-short.46",
doi = "10.18653/v1/2024.acl-short.46",
pages = "501--509",
abstract = "In this paper, we introduce Neural Information Retrieval resources for 11 widely spoken Indian Languages (Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, and Telugu) from two major Indian language families (Indo-Aryan and Dravidian). These resources include (a) INDIC-MARCO, a multilingual version of the MS MARCO dataset in 11 Indian Languages created using Machine Translation, and (b) Indic-ColBERT, a collection of 11 distinct Monolingual Neural Information Retrieval models, each trained on one of the 11 languages in the INDIC-MARCO dataset. To the best of our knowledge, IndicIRSuite is the first attempt at building large-scale Neural Information Retrieval resources for a large number of Indian languages, and we hope that it will help accelerate research in Neural IR for Indian Languages. Experiments demonstrate that Indic-ColBERT achieves 47.47{\%} improvement in the MRR@10 score averaged over the INDIC-MARCO baselines for all 11 Indian languages except Oriya, 12.26{\%} improvement in the NDCG@10 score averaged over the MIRACL Bengali and Hindi Language baselines, and 20{\%} improvement in the MRR@100 Score over the Mr. Tydi Bengali Language baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haq-etal-2024-indicirsuite">
<titleInfo>
<title>IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saiful</namePart>
<namePart type="family">Haq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Khattab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niyati</namePart>
<namePart type="family">Chhaya</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>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce Neural Information Retrieval resources for 11 widely spoken Indian Languages (Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, and Telugu) from two major Indian language families (Indo-Aryan and Dravidian). These resources include (a) INDIC-MARCO, a multilingual version of the MS MARCO dataset in 11 Indian Languages created using Machine Translation, and (b) Indic-ColBERT, a collection of 11 distinct Monolingual Neural Information Retrieval models, each trained on one of the 11 languages in the INDIC-MARCO dataset. To the best of our knowledge, IndicIRSuite is the first attempt at building large-scale Neural Information Retrieval resources for a large number of Indian languages, and we hope that it will help accelerate research in Neural IR for Indian Languages. Experiments demonstrate that Indic-ColBERT achieves 47.47% improvement in the MRR@10 score averaged over the INDIC-MARCO baselines for all 11 Indian languages except Oriya, 12.26% improvement in the NDCG@10 score averaged over the MIRACL Bengali and Hindi Language baselines, and 20% improvement in the MRR@100 Score over the Mr. Tydi Bengali Language baseline.</abstract>
<identifier type="citekey">haq-etal-2024-indicirsuite</identifier>
<identifier type="doi">10.18653/v1/2024.acl-short.46</identifier>
<location>
<url>https://aclanthology.org/2024.acl-short.46</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>501</start>
<end>509</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages
%A Haq, Saiful
%A Sharma, Ashutosh
%A Khattab, Omar
%A Chhaya, Niyati
%A Bhattacharyya, Pushpak
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F haq-etal-2024-indicirsuite
%X In this paper, we introduce Neural Information Retrieval resources for 11 widely spoken Indian Languages (Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, and Telugu) from two major Indian language families (Indo-Aryan and Dravidian). These resources include (a) INDIC-MARCO, a multilingual version of the MS MARCO dataset in 11 Indian Languages created using Machine Translation, and (b) Indic-ColBERT, a collection of 11 distinct Monolingual Neural Information Retrieval models, each trained on one of the 11 languages in the INDIC-MARCO dataset. To the best of our knowledge, IndicIRSuite is the first attempt at building large-scale Neural Information Retrieval resources for a large number of Indian languages, and we hope that it will help accelerate research in Neural IR for Indian Languages. Experiments demonstrate that Indic-ColBERT achieves 47.47% improvement in the MRR@10 score averaged over the INDIC-MARCO baselines for all 11 Indian languages except Oriya, 12.26% improvement in the NDCG@10 score averaged over the MIRACL Bengali and Hindi Language baselines, and 20% improvement in the MRR@100 Score over the Mr. Tydi Bengali Language baseline.
%R 10.18653/v1/2024.acl-short.46
%U https://aclanthology.org/2024.acl-short.46
%U https://doi.org/10.18653/v1/2024.acl-short.46
%P 501-509
Markdown (Informal)
[IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages](https://aclanthology.org/2024.acl-short.46) (Haq et al., ACL 2024)
ACL