Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yice, Zeng, Jie, Hu, Weiming, Wang, Ziyi, Chen, Shiwei, Xu, Ruifeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910502393741312
author Zhang, Yice
Zeng, Jie
Hu, Weiming
Wang, Ziyi
Chen, Shiwei
Xu, Ruifeng
author_facet Zhang, Yice
Zeng, Jie
Hu, Weiming
Wang, Ziyi
Chen, Shiwei
Xu, Ruifeng
contents Aspect Sentiment Quad Prediction (ASQP) aims to predict all quads (aspect term, aspect category, opinion term, sentiment polarity) for a given review, which is the most representative and challenging task in aspect-based sentiment analysis. A key challenge in the ASQP task is the scarcity of labeled data, which limits the performance of existing methods. To tackle this issue, we propose a self-training framework with a pseudo-label scorer, wherein a scorer assesses the match between reviews and their pseudo-labels, aiming to filter out mismatches and thereby enhance the effectiveness of self-training. We highlight two critical aspects to ensure the scorer's effectiveness and reliability: the quality of the training dataset and its model architecture. To this end, we create a human-annotated comparison dataset and train a generative model on it using ranking-based objectives. Extensive experiments on public ASQP datasets reveal that using our scorer can greatly and consistently improve the effectiveness of self-training. Moreover, we explore the possibility of replacing humans with large language models for comparison dataset annotation, and experiments demonstrate its feasibility. We release our code and data at https://github.com/HITSZ-HLT/ST-w-Scorer-ABSA .
format Preprint
id arxiv_https___arxiv_org_abs_2406_18078
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction
Zhang, Yice
Zeng, Jie
Hu, Weiming
Wang, Ziyi
Chen, Shiwei
Xu, Ruifeng
Computation and Language
Artificial Intelligence
Aspect Sentiment Quad Prediction (ASQP) aims to predict all quads (aspect term, aspect category, opinion term, sentiment polarity) for a given review, which is the most representative and challenging task in aspect-based sentiment analysis. A key challenge in the ASQP task is the scarcity of labeled data, which limits the performance of existing methods. To tackle this issue, we propose a self-training framework with a pseudo-label scorer, wherein a scorer assesses the match between reviews and their pseudo-labels, aiming to filter out mismatches and thereby enhance the effectiveness of self-training. We highlight two critical aspects to ensure the scorer's effectiveness and reliability: the quality of the training dataset and its model architecture. To this end, we create a human-annotated comparison dataset and train a generative model on it using ranking-based objectives. Extensive experiments on public ASQP datasets reveal that using our scorer can greatly and consistently improve the effectiveness of self-training. Moreover, we explore the possibility of replacing humans with large language models for comparison dataset annotation, and experiments demonstrate its feasibility. We release our code and data at https://github.com/HITSZ-HLT/ST-w-Scorer-ABSA .
title Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.18078