Relation-Aware Collaborative Learning for Unified Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) involves three subtasks, i.e., aspect term extraction, opinion term extraction, and aspect-level sentiment classification. Most existing studies focused on one of these subtasks only. Several recent researches made successful attempts to solve the complete ABSA problem with a unified framework. However, the interactive relations among three subtasks are still under-exploited. We argue that such relations encode collaborative signals between different subtasks. For example, when the opinion term is \textit{{``}delicious{''}}, the aspect term must be \textit{{``}food{''}} rather than \textit{{``}place{''}}. In order to fully exploit these relations, we propose a Relation-Aware Collaborative Learning (RACL) framework which allows the subtasks to work coordinately via the multi-task learning and relation propagation mechanisms in a stacked multi-layer network. Extensive experiments on three real-world datasets demonstrate that RACL significantly outperforms the state-of-the-art methods for the complete ABSA task.
PDF AbstractCode
Datasets
Results from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Aspect Term Extraction and Sentiment Classification | SemEval | RACL-BERT | Avg F1 | 68.29 | # 4 | |
Restaurant 2014 (F1) | 75.42 | # 3 | ||||
Laptop 2014 (F1) | 63.4 | # 4 | ||||
Restaurant 2015 (F1) | 66.05 | # 2 | ||||
Aspect-Based Sentiment Analysis (ABSA) | SemEval 2014 Task 4 Laptop | RACL-BERT | F1 | 63.4 | # 4 | |
Sentiment Analysis | SemEval 2014 Task 4 Subtask 1+2 | RACL-BERT | F1 | 63.4 | # 4 | |
Aspect-Based Sentiment Analysis (ABSA) | SemEval 2014 Task 4 Subtask 1+2 | RACL-BERT | F1 | 63.4 | # 6 |