Salvato in:
Dettagli Bibliografici
Autori principali: Ding, Xuanwen, Zhou, Jie, Dou, Liang, Chen, Qin, Wu, Yuanbin, Chen, Chengcai, He, Liang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.05496
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914789158027264
author Ding, Xuanwen
Zhou, Jie
Dou, Liang
Chen, Qin
Wu, Yuanbin
Chen, Chengcai
He, Liang
author_facet Ding, Xuanwen
Zhou, Jie
Dou, Liang
Chen, Qin
Wu, Yuanbin
Chen, Chengcai
He, Liang
contents Aspect-based sentiment analysis (ABSA) is an important subtask of sentiment analysis, which aims to extract the aspects and predict their sentiments. Most existing studies focus on improving the performance of the target domain by fine-tuning domain-specific models (trained on source domains) based on the target domain dataset. Few works propose continual learning tasks for ABSA, which aim to learn the target domain's ability while maintaining the history domains' abilities. In this paper, we propose a Large Language Model-based Continual Learning (\texttt{LLM-CL}) model for ABSA. First, we design a domain knowledge decoupling module to learn a domain-invariant adapter and separate domain-variant adapters dependently with an orthogonal constraint. Then, we introduce a domain knowledge warmup strategy to align the representation between domain-invariant and domain-variant knowledge. In the test phase, we index the corresponding domain-variant knowledge via domain positioning to not require each sample's domain ID. Extensive experiments over 19 datasets indicate that our \texttt{LLM-CL} model obtains new state-of-the-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05496
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysis
Ding, Xuanwen
Zhou, Jie
Dou, Liang
Chen, Qin
Wu, Yuanbin
Chen, Chengcai
He, Liang
Computation and Language
Aspect-based sentiment analysis (ABSA) is an important subtask of sentiment analysis, which aims to extract the aspects and predict their sentiments. Most existing studies focus on improving the performance of the target domain by fine-tuning domain-specific models (trained on source domains) based on the target domain dataset. Few works propose continual learning tasks for ABSA, which aim to learn the target domain's ability while maintaining the history domains' abilities. In this paper, we propose a Large Language Model-based Continual Learning (\texttt{LLM-CL}) model for ABSA. First, we design a domain knowledge decoupling module to learn a domain-invariant adapter and separate domain-variant adapters dependently with an orthogonal constraint. Then, we introduce a domain knowledge warmup strategy to align the representation between domain-invariant and domain-variant knowledge. In the test phase, we index the corresponding domain-variant knowledge via domain positioning to not require each sample's domain ID. Extensive experiments over 19 datasets indicate that our \texttt{LLM-CL} model obtains new state-of-the-art performance.
title Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysis
topic Computation and Language
url https://arxiv.org/abs/2405.05496