Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Jieyong, Heo, Ryang, Seo, Yongsik, Kang, SeongKu, Yeo, Jinyoung, Lee, Dongha
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914957452378112
author Kim, Jieyong
Heo, Ryang
Seo, Yongsik
Kang, SeongKu
Yeo, Jinyoung
Lee, Dongha
author_facet Kim, Jieyong
Heo, Ryang
Seo, Yongsik
Kang, SeongKu
Yeo, Jinyoung
Lee, Dongha
contents In the task of aspect sentiment quad prediction (ASQP), generative methods for predicting sentiment quads have shown promising results. However, they still suffer from imprecise predictions and limited interpretability, caused by data scarcity and inadequate modeling of the quadruplet composition process. In this paper, we propose Self-Consistent Reasoning-based Aspect-sentiment quadruple Prediction (SCRAP), optimizing its model to generate reasonings and the corresponding sentiment quadruplets in sequence. SCRAP adopts the Extract-Then-Assign reasoning strategy, which closely mimics human cognition. In the end, SCRAP significantly improves the model's ability to handle complex reasoning tasks and correctly predict quadruplets through consistency voting, resulting in enhanced interpretability and accuracy in ASQP.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy
Kim, Jieyong
Heo, Ryang
Seo, Yongsik
Kang, SeongKu
Yeo, Jinyoung
Lee, Dongha
Computation and Language
In the task of aspect sentiment quad prediction (ASQP), generative methods for predicting sentiment quads have shown promising results. However, they still suffer from imprecise predictions and limited interpretability, caused by data scarcity and inadequate modeling of the quadruplet composition process. In this paper, we propose Self-Consistent Reasoning-based Aspect-sentiment quadruple Prediction (SCRAP), optimizing its model to generate reasonings and the corresponding sentiment quadruplets in sequence. SCRAP adopts the Extract-Then-Assign reasoning strategy, which closely mimics human cognition. In the end, SCRAP significantly improves the model's ability to handle complex reasoning tasks and correctly predict quadruplets through consistency voting, resulting in enhanced interpretability and accuracy in ASQP.
title Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy
topic Computation and Language
url https://arxiv.org/abs/2403.00354