@inproceedings{tian-etal-2025-ruc,
title = "{RUC} Team at {S}em{E}val-2025 Task 5: Fast Automated Subject Indexing: A Method Based on Similar Records Matching and Related Subject Ranking",
author = "Tian, Xia and
Xin, Yang and
Jing, Wu and
Heng, Xiu and
Xin, Zhang and
Yu, Li and
Tong, Gao and
Xi, Tan and
Dong, Hu and
Tao, Chen and
Zhi, Jia",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.317/",
pages = "2437--2442",
ISBN = "979-8-89176-273-2",
abstract = "This paper presents MaRSI, an automatic subject indexing method designed to address the limitations of traditional manual indexing and emerging GenAI technologies. Focusing on improving indexing accuracy in cross-lingual contexts and balancing efficiency and accuracy in large-scale datasets, MaRSI mimics human reference learning behavior by constructing semantic indexes from pre-indexed document. It calculates similarity to retrieve relevant references, merges, and reorders their topics to generate index results. Experiments demonstrate that MaRSI outperforms supervised fine-tuning of LLMs on the same dataset, offering advantages in speed, effectiveness, and interpretability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-etal-2025-ruc">
<titleInfo>
<title>RUC Team at SemEval-2025 Task 5: Fast Automated Subject Indexing: A Method Based on Similar Records Matching and Related Subject Ranking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xia</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Xin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wu</namePart>
<namePart type="family">Jing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiu</namePart>
<namePart type="family">Heng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Xin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gao</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tan</namePart>
<namePart type="family">Xi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hu</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="family">Zhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-273-2</identifier>
</relatedItem>
<abstract>This paper presents MaRSI, an automatic subject indexing method designed to address the limitations of traditional manual indexing and emerging GenAI technologies. Focusing on improving indexing accuracy in cross-lingual contexts and balancing efficiency and accuracy in large-scale datasets, MaRSI mimics human reference learning behavior by constructing semantic indexes from pre-indexed document. It calculates similarity to retrieve relevant references, merges, and reorders their topics to generate index results. Experiments demonstrate that MaRSI outperforms supervised fine-tuning of LLMs on the same dataset, offering advantages in speed, effectiveness, and interpretability.</abstract>
<identifier type="citekey">tian-etal-2025-ruc</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.317/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2437</start>
<end>2442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RUC Team at SemEval-2025 Task 5: Fast Automated Subject Indexing: A Method Based on Similar Records Matching and Related Subject Ranking
%A Tian, Xia
%A Xin, Yang
%A Jing, Wu
%A Heng, Xiu
%A Xin, Zhang
%A Yu, Li
%A Tong, Gao
%A Xi, Tan
%A Dong, Hu
%A Tao, Chen
%A Zhi, Jia
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F tian-etal-2025-ruc
%X This paper presents MaRSI, an automatic subject indexing method designed to address the limitations of traditional manual indexing and emerging GenAI technologies. Focusing on improving indexing accuracy in cross-lingual contexts and balancing efficiency and accuracy in large-scale datasets, MaRSI mimics human reference learning behavior by constructing semantic indexes from pre-indexed document. It calculates similarity to retrieve relevant references, merges, and reorders their topics to generate index results. Experiments demonstrate that MaRSI outperforms supervised fine-tuning of LLMs on the same dataset, offering advantages in speed, effectiveness, and interpretability.
%U https://aclanthology.org/2025.semeval-1.317/
%P 2437-2442
Markdown (Informal)
[RUC Team at SemEval-2025 Task 5: Fast Automated Subject Indexing: A Method Based on Similar Records Matching and Related Subject Ranking](https://aclanthology.org/2025.semeval-1.317/) (Tian et al., SemEval 2025)
ACL
- Xia Tian, Yang Xin, Wu Jing, Xiu Heng, Zhang Xin, Li Yu, Gao Tong, Tan Xi, Hu Dong, Chen Tao, and Jia Zhi. 2025. RUC Team at SemEval-2025 Task 5: Fast Automated Subject Indexing: A Method Based on Similar Records Matching and Related Subject Ranking. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2437–2442, Vienna, Austria. Association for Computational Linguistics.