Dual Encoder: Exploiting the Potential of Syntactic and Semantic for Aspect Sentiment Triplet Extraction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhao, Xiaowei, Zhou, Yong, Xu, Xiujuan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911782971375616
author Zhao, Xiaowei
Zhou, Yong
Xu, Xiujuan
author_facet Zhao, Xiaowei
Zhou, Yong
Xu, Xiujuan
contents Aspect Sentiment Triple Extraction (ASTE) is an emerging task in fine-grained sentiment analysis. Recent studies have employed Graph Neural Networks (GNN) to model the syntax-semantic relationships inherent in triplet elements. However, they have yet to fully tap into the vast potential of syntactic and semantic information within the ASTE task. In this work, we propose a \emph{Dual Encoder: Exploiting the potential of Syntactic and Semantic} model (D2E2S), which maximizes the syntactic and semantic relationships among words. Specifically, our model utilizes a dual-channel encoder with a BERT channel to capture semantic information, and an enhanced LSTM channel for comprehensive syntactic information capture. Subsequently, we introduce the heterogeneous feature interaction module to capture intricate interactions between dependency syntax and attention semantics, and to dynamically select vital nodes. We leverage the synergy of these modules to harness the significant potential of syntactic and semantic information in ASTE tasks. Testing on public benchmarks, our D2E2S model surpasses the current state-of-the-art(SOTA), demonstrating its effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2402_15370
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dual Encoder: Exploiting the Potential of Syntactic and Semantic for Aspect Sentiment Triplet Extraction
Zhao, Xiaowei
Zhou, Yong
Xu, Xiujuan
Computation and Language
Artificial Intelligence
Machine Learning
Aspect Sentiment Triple Extraction (ASTE) is an emerging task in fine-grained sentiment analysis. Recent studies have employed Graph Neural Networks (GNN) to model the syntax-semantic relationships inherent in triplet elements. However, they have yet to fully tap into the vast potential of syntactic and semantic information within the ASTE task. In this work, we propose a \emph{Dual Encoder: Exploiting the potential of Syntactic and Semantic} model (D2E2S), which maximizes the syntactic and semantic relationships among words. Specifically, our model utilizes a dual-channel encoder with a BERT channel to capture semantic information, and an enhanced LSTM channel for comprehensive syntactic information capture. Subsequently, we introduce the heterogeneous feature interaction module to capture intricate interactions between dependency syntax and attention semantics, and to dynamically select vital nodes. We leverage the synergy of these modules to harness the significant potential of syntactic and semantic information in ASTE tasks. Testing on public benchmarks, our D2E2S model surpasses the current state-of-the-art(SOTA), demonstrating its effectiveness.
title Dual Encoder: Exploiting the Potential of Syntactic and Semantic for Aspect Sentiment Triplet Extraction
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.15370