@inproceedings{zhukova-etal-2025-automated,
title = "Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language",
author = "Zhukova, Anastasia and
Matt, Christian E. and
Gipp, Bela",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.8/",
pages = "112--122",
abstract = "Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain knowledge and training for the annotation task. This study addresses the challenge of automated collecting test datasets to evaluate semantic search in low-resource domain-specific German language of the process industry. Our approach proposes an end-to-end annotation pipeline for automated query generation to the score reassessment of query-document pairs. To overcome the lack of text encoders trained in the German chemistry domain, we explore a principle of an ensemble of {\textquotedblleft}weak{\textquotedblright} text encoders trained on common knowledge datasets. We combine individual relevance scores from diverse models to retrieve document candidates and relevance scores generated by an LLM, aiming to achieve consensus on query-document alignment. Evaluation results demonstrate that the ensemble method significantly improves alignment with human-assigned relevance scores, outperforming individual models in both inter-coder agreement and accuracy metrics. These findings suggest that ensemble learning can effectively adapt semantic search systems for specialized, low-resource languages, offering a practical solution to resource limitations in domain-specific contexts."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhukova-etal-2025-automated">
<titleInfo>
<title>Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Zhukova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Matt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bela</namePart>
<namePart type="family">Gipp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Models for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain knowledge and training for the annotation task. This study addresses the challenge of automated collecting test datasets to evaluate semantic search in low-resource domain-specific German language of the process industry. Our approach proposes an end-to-end annotation pipeline for automated query generation to the score reassessment of query-document pairs. To overcome the lack of text encoders trained in the German chemistry domain, we explore a principle of an ensemble of “weak” text encoders trained on common knowledge datasets. We combine individual relevance scores from diverse models to retrieve document candidates and relevance scores generated by an LLM, aiming to achieve consensus on query-document alignment. Evaluation results demonstrate that the ensemble method significantly improves alignment with human-assigned relevance scores, outperforming individual models in both inter-coder agreement and accuracy metrics. These findings suggest that ensemble learning can effectively adapt semantic search systems for specialized, low-resource languages, offering a practical solution to resource limitations in domain-specific contexts.</abstract>
<identifier type="citekey">zhukova-etal-2025-automated</identifier>
<location>
<url>https://aclanthology.org/2025.loreslm-1.8/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>112</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language
%A Zhukova, Anastasia
%A Matt, Christian E.
%A Gipp, Bela
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the First Workshop on Language Models for Low-Resource Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhukova-etal-2025-automated
%X Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain knowledge and training for the annotation task. This study addresses the challenge of automated collecting test datasets to evaluate semantic search in low-resource domain-specific German language of the process industry. Our approach proposes an end-to-end annotation pipeline for automated query generation to the score reassessment of query-document pairs. To overcome the lack of text encoders trained in the German chemistry domain, we explore a principle of an ensemble of “weak” text encoders trained on common knowledge datasets. We combine individual relevance scores from diverse models to retrieve document candidates and relevance scores generated by an LLM, aiming to achieve consensus on query-document alignment. Evaluation results demonstrate that the ensemble method significantly improves alignment with human-assigned relevance scores, outperforming individual models in both inter-coder agreement and accuracy metrics. These findings suggest that ensemble learning can effectively adapt semantic search systems for specialized, low-resource languages, offering a practical solution to resource limitations in domain-specific contexts.
%U https://aclanthology.org/2025.loreslm-1.8/
%P 112-122
Markdown (Informal)
[Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language](https://aclanthology.org/2025.loreslm-1.8/) (Zhukova et al., LoResLM 2025)
ACL