Meta-Based Self-Training and Re-Weighting for Aspect-Based Sentiment Analysis
- 30 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 14 (3) , 1731-1742
Abstract
Aspect-based sentiment analysis (ABSA) means to identify fine-grained aspects, opinions, and sentiment polarities. Recent ABSA research focuses on utilizing multi-task learning (MTL) to achieve less computational costs and better performance. However, there are certain limits in MTL-based ABSA. For example, unbalanced labels and sub-task learning difficulties may result in the biases that some labels and sub-tasks are overfitting, while the others are underfitting. To address these issues, inspired by neuro-symbolic learning systems, we propose a meta-based self-training method with a meta-weighter (MSM). We believe that a generalizable model can be achieved by appropriate symbolic representation selection (in-domain knowledge) and effective learning control (regulation) in a neural system. Thus, MSM trains a teacher model to generate in-domain knowledge (e.g., unlabeled data selection and pseudo-label generation), where the generated pseudo-labels are used by a student model for supervised learning. Then, the meta-weighter of MSM is jointly trained with the student model to provide each instance with sub-task-specific weights to coordinate their convergence rates, balancing class labels, and alleviating noise impacts introduced from self-training. The following experiments indicate that MSM can utilize 50% labeled data to achieve comparable results to state-of-arts models in ABSA and outperform them with all labeled data.Keywords
Funding Information
- Key Research and Development Program of Ningxia Hui Nationality Autonomous Region (2022BEG02025)
- Key Research and Development Program of Shaanxi Province (2021GXLH-Z-095)
- Industry Alignment Fund â Industry Collaboration Projects (RIE2020)
- Innovative Research Group of the National Natural Science Foundation of China (61721002)
- Innovation Research Team of the Ministry of Education
- Project of China Knowledge Centre for Engineering Science and Technology (IRT_17R86)
This publication has 33 references indexed in Scilit:
- Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification2019
- An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis2019
- End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories2019
- Aspect Term Extraction with History Attention and Selective Transformation2018
- Word Embedding and WordNet Based Metaphor Identification and Interpretation2018
- Focal Loss for Dense Object Detection2017
- SemEval-2015 Task 12: Aspect Based Sentiment Analysis2015
- SemEval-2014 Task 4: Aspect Based Sentiment Analysis2014
- Curriculum learning2009
- Bootstrapping POS taggers using unlabelled data2003