Saved in:
Bibliographic Details
Main Authors: Jun, Yonghyun, Lee, Hwanhee
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.11130
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908477283106816
author Jun, Yonghyun
Lee, Hwanhee
author_facet Jun, Yonghyun
Lee, Hwanhee
contents Aspect-based sentiment analysis (ABSA) assesses sentiments towards specific aspects within texts, resulting in detailed sentiment tuples. Previous ABSA models often use static templates to predict all of the elements in the tuples, and these models often fail to accurately capture dependencies between elements. Multi-view prompting method improves the performance of ABSA by predicting tuples with various templates and then ensembling the results. However, this method suffers from inefficiencies and out-of-distribution errors. In this paper, we propose a Dynamic Order Template (DOT) method for ABSA, which dynamically generates necessary views for each instance based on instance-level entropy. Ensuring the diverse and relevant view generation, our proposed method improves F1-scores on ASQP and ACOS datasets while significantly reducing inference time.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11130
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis
Jun, Yonghyun
Lee, Hwanhee
Computation and Language
Aspect-based sentiment analysis (ABSA) assesses sentiments towards specific aspects within texts, resulting in detailed sentiment tuples. Previous ABSA models often use static templates to predict all of the elements in the tuples, and these models often fail to accurately capture dependencies between elements. Multi-view prompting method improves the performance of ABSA by predicting tuples with various templates and then ensembling the results. However, this method suffers from inefficiencies and out-of-distribution errors. In this paper, we propose a Dynamic Order Template (DOT) method for ABSA, which dynamically generates necessary views for each instance based on instance-level entropy. Ensuring the diverse and relevant view generation, our proposed method improves F1-scores on ASQP and ACOS datasets while significantly reducing inference time.
title Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis
topic Computation and Language
url https://arxiv.org/abs/2406.11130