@inproceedings{wojtasik-etal-2024-beir,
title = "{BEIR}-{PL}: Zero Shot Information Retrieval Benchmark for the {P}olish Language",
author = "Wojtasik, Konrad and
Wo{\l}owiec, Kacper and
Shishkin, Vadim and
Janz, Arkadiusz and
Piasecki, Maciej",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.194/",
pages = "2149--2160",
abstract = "The BEIR dataset is a large, heterogeneous benchmark for Information Retrieval (IR), garnering considerable attention within the research community. However, BEIR and analogous datasets are predominantly restricted to English language. Our objective is to establish extensive large-scale resources for IR in the Polish language, thereby advancing the research in this NLP area. In this work, inspired by mMARCO and Mr. TyDi datasets, we translated all accessible open IR datasets into Polish, and we introduced the BEIR-PL benchmark {--} a new benchmark which comprises 13 datasets, facilitating further development, training and evaluation of modern Polish language models for IR tasks. We executed an evaluation and comparison of numerous IR models on the newly introduced BEIR-PL benchmark. Furthermore, we publish pre-trained open IR models for Polish language, marking a pioneering development in this field. The BEIR-PL is included in MTEB Benchmark and also available with trained models at URL \url{https://huggingface.co/clarin-knext}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wojtasik-etal-2024-beir">
<titleInfo>
<title>BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Konrad</namePart>
<namePart type="family">Wojtasik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kacper</namePart>
<namePart type="family">Wołowiec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vadim</namePart>
<namePart type="family">Shishkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arkadiusz</namePart>
<namePart type="family">Janz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Piasecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The BEIR dataset is a large, heterogeneous benchmark for Information Retrieval (IR), garnering considerable attention within the research community. However, BEIR and analogous datasets are predominantly restricted to English language. Our objective is to establish extensive large-scale resources for IR in the Polish language, thereby advancing the research in this NLP area. In this work, inspired by mMARCO and Mr. TyDi datasets, we translated all accessible open IR datasets into Polish, and we introduced the BEIR-PL benchmark – a new benchmark which comprises 13 datasets, facilitating further development, training and evaluation of modern Polish language models for IR tasks. We executed an evaluation and comparison of numerous IR models on the newly introduced BEIR-PL benchmark. Furthermore, we publish pre-trained open IR models for Polish language, marking a pioneering development in this field. The BEIR-PL is included in MTEB Benchmark and also available with trained models at URL https://huggingface.co/clarin-knext.</abstract>
<identifier type="citekey">wojtasik-etal-2024-beir</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.194/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2149</start>
<end>2160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language
%A Wojtasik, Konrad
%A Wołowiec, Kacper
%A Shishkin, Vadim
%A Janz, Arkadiusz
%A Piasecki, Maciej
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F wojtasik-etal-2024-beir
%X The BEIR dataset is a large, heterogeneous benchmark for Information Retrieval (IR), garnering considerable attention within the research community. However, BEIR and analogous datasets are predominantly restricted to English language. Our objective is to establish extensive large-scale resources for IR in the Polish language, thereby advancing the research in this NLP area. In this work, inspired by mMARCO and Mr. TyDi datasets, we translated all accessible open IR datasets into Polish, and we introduced the BEIR-PL benchmark – a new benchmark which comprises 13 datasets, facilitating further development, training and evaluation of modern Polish language models for IR tasks. We executed an evaluation and comparison of numerous IR models on the newly introduced BEIR-PL benchmark. Furthermore, we publish pre-trained open IR models for Polish language, marking a pioneering development in this field. The BEIR-PL is included in MTEB Benchmark and also available with trained models at URL https://huggingface.co/clarin-knext.
%U https://aclanthology.org/2024.lrec-main.194/
%P 2149-2160
Markdown (Informal)
[BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language](https://aclanthology.org/2024.lrec-main.194/) (Wojtasik et al., LREC-COLING 2024)
ACL