基于术语提示双路文本生成的方面情感三元组抽取  

Term-Prompted and Dual-Path Text Generation for Aspect Sentiment Triplet Extraction

作　　者：李银强 蓝天[2] 刘瑶[1] 向飛阳 孙丽纯 杜知涵 刘峤[2] Li Yinqiang;Lan Tian;Liu Yao;Xiang Feiyang;Sun Lichun;Du Zhihan;Liu Qiao(School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu 610054;School of Computer Science and Engineering,University of Electronic Science and Technology of China,Chengdu 611731)

机构地区：[1]电子科技大学信息与软件工程学院,成都610054 [2]电子科技大学计算机科学与工程学院,成都611731

出　　处：《计算机研究与发展》2025年第4期915-929,共15页Journal of Computer Research and Development

摘　　要：方面情感三元组抽取(aspect sentiment triplet extraction,ASTE)是方面级情感分析(aspect based sentiment analysis,ABSA)中具有挑战性的子任务之一,旨在从文本中抽取方面术语、观点术语和情感极性三元组.近期基于生成式的抽取方法取得了出色的表现,这些方法通过顺序串联目标三元组来实现自回归式三元组生成.然而,这种串联方法可能导致无序三元组之间存在顺序依赖,从而在解码过程中引入错误累积.为解决这个问题,提出了基于术语提示双路文本生成(term-prompted and dual-path text generation,TePDuP)的方法.该方法首先利用机器阅读理解(machine reading comprehension,MRC)实现方面术语和观点术语的并行化抽取,然后将它们作为提示前缀来引导条件式三元组的生成,形成双路文本生成框架.同时,在训练阶段引入计划采样的方法来修正MRC抽取错误所带来的偏差.为进一步提高性能,引入生成概率将方面术语和观点术语引导的结果合并,以增强模型的鲁棒性.基于ASTE-DATA-V2数据集的实验结果表明,提出的方法是有效的且明显优于其他基线模型,并给出具体案例分析,证明该方法一定程度上解决了前述问题.Aspect sentiment triplet extraction(ASTE)is a challenging subtask within aspect-based sentiment analysis.It aims to extract triplets consisting of aspect terms,opinion terms,and sentiment polarities from texts.In the recent past,generative extraction techniques have demonstrated remarkable efficacy through the sequential concatenation of target triplets,thereby enabling the autoregressive generation of triplets.However,this concatenation method may lead to sequential dependencies among unrelated triplets,introducing error accumulation during decoding.To address this issue,we propose a term-prompted and dual-path text generation(TePDuP)method.This method first utilizes machine reading comprehension(MRC)to extract aspect and opinion term in parallel,and then uses them as prompt prefixes to guide conditional triplet generation,forming a dual-path text generation framework.Meanwhile,during the training phase,we incorporate scheduled sampling as a corrective measure to mitigate the bias stemming from MRC extraction.Furthermore,in order to enhance performance to an even greater extent,we incorporate generation probabilities to merge outcomes guided by aspect and opinion terms,thereby augmenting the resilience of the model.Experimental results on the ASTE-DATA-V2 dataset show that the proposed method is effective and significantly outperforms other baseline models,and provide case studies to demonstrate that the method solves the aforementioned problem to some extent.

关 键 词：方面级情感分析 三元组抽取 文本生成 机器阅读理解 计划采样 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]