LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F25%3A43976214" target="_blank" >RIV/49777513:23520/25:43976214 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.acl-long.41/" target="_blank" >https://aclanthology.org/2025.acl-long.41/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2025.acl-long.41" target="_blank" >10.18653/v1/2025.acl-long.41</a>

Jazyk výsledku

angličtina

Název v původním jazyce

LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation

Popis výsledku v původním jazyce

Cross-lingual aspect-based sentiment analysis (ABSA) involves detailed sentiment analysis in a target language by transferring knowledge from a source language with available annotated data. Most existing methods depend heavily on often unreliable translation tools to bridge the language gap. In this paper, we propose a new approach that leverages a large language model (LLM) to generate high-quality pseudo-labelled data in the target language without the need for translation tools. First, the framework trains an ABSA model to obtain predictions for unlabelled target language data. Next, LLM is prompted to generate natural sentences that better represent these noisy predictions than the original text. The ABSA model is then further fine-tuned on the resulting pseudo-labelled dataset. We demonstrate the effectiveness of this method across six languages and five backbone models, surpassing previous state-of-the-art translation-based approaches. The proposed framework also supports generative models, and we show that fine-tuned LLMs outperform smaller multilingual models.

Název v anglickém jazyce

LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation

Popis výsledku anglicky

Cross-lingual aspect-based sentiment analysis (ABSA) involves detailed sentiment analysis in a target language by transferring knowledge from a source language with available annotated data. Most existing methods depend heavily on often unreliable translation tools to bridge the language gap. In this paper, we propose a new approach that leverages a large language model (LLM) to generate high-quality pseudo-labelled data in the target language without the need for translation tools. First, the framework trains an ABSA model to obtain predictions for unlabelled target language data. Next, LLM is prompted to generate natural sentences that better represent these noisy predictions than the original text. The ABSA model is then further fine-tuned on the resulting pseudo-labelled dataset. We demonstrate the effectiveness of this method across six languages and five backbone models, surpassing previous state-of-the-art translation-based approaches. The proposed framework also supports generative models, and we show that fine-tuned LLMs outperform smaller multilingual models.

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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

ISBN

979-8-89176-251-0

ISSN

—

e-ISSN

—

Počet stran výsledku

15

Strana od-do

839-853

Název nakladatele

Association for Computational Linguistics

Místo vydání

Kerrville

Místo konání akce

Vídeň

Datum konání akce

27. 7. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001596029800041