Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Xiancai, Zhang, Jia-Dong, Xiong, Lei, Liu, Zhishang
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2311.03896
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913400477450240
author Xu, Xiancai
Zhang, Jia-Dong
Xiong, Lei
Liu, Zhishang
author_facet Xu, Xiancai
Zhang, Jia-Dong
Xiong, Lei
Liu, Zhishang
contents Aspect-based sentiment analysis (ABSA) have been extensively studied, but little light has been shed on the quadruple extraction consisting of four fundamental elements: aspects, categories, opinions and sentiments, especially with implicit aspects and opinions. In this paper, we propose a new method iACOS for extracting Implicit Aspects with Categories and Opinions with Sentiments. First, iACOS appends two implicit tokens at the end of a text to capture the context-aware representation of all tokens including implicit aspects and opinions. Second, iACOS develops a sequence labeling model over the context-aware token representation to co-extract explicit and implicit aspects and opinions. Third, iACOS devises a multi-label classifier with a specialized multi-head attention for discovering aspect-opinion pairs and predicting their categories and sentiments simultaneously. Fourth, iACOS leverages informative and adaptive negative examples to jointly train the multi-label classifier and the other two classifiers on categories and sentiments by multi-task learning. Finally, the experimental results show that iACOS significantly outperforms other quadruple extraction baselines according to the F1 score on two public benchmark datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2311_03896
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examples
Xu, Xiancai
Zhang, Jia-Dong
Xiong, Lei
Liu, Zhishang
Computation and Language
Aspect-based sentiment analysis (ABSA) have been extensively studied, but little light has been shed on the quadruple extraction consisting of four fundamental elements: aspects, categories, opinions and sentiments, especially with implicit aspects and opinions. In this paper, we propose a new method iACOS for extracting Implicit Aspects with Categories and Opinions with Sentiments. First, iACOS appends two implicit tokens at the end of a text to capture the context-aware representation of all tokens including implicit aspects and opinions. Second, iACOS develops a sequence labeling model over the context-aware token representation to co-extract explicit and implicit aspects and opinions. Third, iACOS devises a multi-label classifier with a specialized multi-head attention for discovering aspect-opinion pairs and predicting their categories and sentiments simultaneously. Fourth, iACOS leverages informative and adaptive negative examples to jointly train the multi-label classifier and the other two classifiers on categories and sentiments by multi-task learning. Finally, the experimental results show that iACOS significantly outperforms other quadruple extraction baselines according to the F1 score on two public benchmark datasets.
title iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examples
topic Computation and Language
url https://arxiv.org/abs/2311.03896