Syngen: A Syntactic Plug-And-Play Module for Generative Aspect-Based Sentiment Analysis
Authors:
- 4 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Aspect-based Sentiment Analysis (ABSA) is a sentiment analysis task at fine-grained level. Recently, generative frameworks have attracted increasing attention in ABSA due to their ability to unify subtasks and their continuity to upstream pre-training tasks. However, these generative models suffer from the neighboring dependency problem that induces neighboring words to get higher attention. In this paper, we propose SynGen, a plug-and-play syntactic information aware module. As a plug-in module, our SynGen can be easily applied to any generative framework backbones. The key insight of our module is to add syntactic inductive bias to attention assignment and thus direct attention to the correct target words. To the best of our knowledge, we are the first ones to introduce syntactic information to generative ABSA frameworks. Our module design is based on two main principles: (1) maintaining the structural integrity of backbone PLMs and (2) disentangling the added syntactic information and original semantic information. Empirical results on four popular ABSA datasets demonstrate that Syn-Gen enhanced model achieves a comparable performance to the state-of-the-art model with relaxed labeling specification and less training consumption.Keywords
All Related Versions
Funding Information
- Research and Development
This publication has 19 references indexed in Scilit:
- Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment AnalysisProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification2020
- Relational Graph Attention Network for Aspect-based Sentiment Analysis2020
- A Unified Model for Opinion Target Extraction and Target Sentiment PredictionProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision2019
- What Does BERT Look at? An Analysis of BERT’s Attention2019
- Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling2019
- SemEval-2016 Task 5: Aspect Based Sentiment Analysis2016
- SemEval-2015 Task 12: Aspect Based Sentiment Analysis2015
- SemEval-2014 Task 4: Aspect Based Sentiment Analysis2014