Advancing Cross-Lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F25%3A43975483" target="_blank" >RIV/49777513:23520/25:43975483 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scitepress.org/PublicationsDetail.aspx?ID=XPUs7tfQdCI=&t=1" target="_blank" >https://www.scitepress.org/PublicationsDetail.aspx?ID=XPUs7tfQdCI=&t=1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0013349400003890" target="_blank" >10.5220/0013349400003890</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Advancing Cross-Lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models

Popis výsledku v původním jazyce

Aspect-based sentiment analysis (ABSA) has made significant strides, yet challenges remain for low-resource languages due to the predominant focus on English. Current cross-lingual ABSA studies often centre on simpler tasks and rely heavily on external translation tools. In this paper, we present a novel sequence-to sequence method for compound ABSA tasks that eliminates the need for such tools. Our approach, which uses constrained decoding, improves cross-lingual ABSA performance by up to 10%. This method broadens the scope of cross-lingual ABSA, enabling it to handle more complex tasks and providing a practical, efficient alternative to translation-dependent techniques. Furthermore, we compare our approach with large language models (LLMs) and show that while fine-tuned multilingual LLMs can achieve comparable results, English centric LLMs struggle with these tasks.

Název v anglickém jazyce

Advancing Cross-Lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models

Popis výsledku anglicky

Aspect-based sentiment analysis (ABSA) has made significant strides, yet challenges remain for low-resource languages due to the predominant focus on English. Current cross-lingual ABSA studies often centre on simpler tasks and rely heavily on external translation tools. In this paper, we present a novel sequence-to sequence method for compound ABSA tasks that eliminates the need for such tools. Our approach, which uses constrained decoding, improves cross-lingual ABSA performance by up to 10%. This method broadens the scope of cross-lingual ABSA, enabling it to handle more complex tasks and providing a practical, efficient alternative to translation-dependent techniques. Furthermore, we compare our approach with large language models (LLMs) and show that while fine-tuned multilingual LLMs can achieve comparable results, English centric LLMs struggle with these tasks.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EH23_021%2F0008436" target="_blank" >EH23_021/0008436: VaV technologií pro pokročilou digitalizaci v plzeňské metropolitní oblasti (DigiTech)</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART

ISBN

978-989-758-737-5

ISSN

2184-433X

e-ISSN

—

Počet stran výsledku

10

Strana od-do

757-766

Název nakladatele

ScitePress

Místo vydání

Setúbal

Místo konání akce

Porto

Datum konání akce

23. 2. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—