Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation
This work addresses aspect term extraction, a subtask in aspect-based sentiment analysis, by improving dependency tree representations, offering a domain-specific incremental advance.
The paper tackled aspect term extraction by proposing a bidirectional dependency tree network to incorporate both bottom-up and top-down propagation on dependency trees, integrated with BiLSTM-CRF for tree-structured and sequential features. Experimental results showed it outperformed state-of-the-art models on four SemEval datasets.
Aspect term extraction is one of the important subtasks in aspect-based sentiment analysis. Previous studies have shown that using dependency tree structure representation is promising for this task. However, most dependency tree structures involve only one directional propagation on the dependency tree. In this paper, we first propose a novel bidirectional dependency tree network to extract dependency structure features from the given sentences. The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree. An end-to-end framework is then developed to integrate the embedded representations and BiLSTM plus CRF to learn both tree-structured and sequential features to solve the aspect term extraction problem. Experimental results demonstrate that the proposed model outperforms state-of-the-art baseline models on four benchmark SemEval datasets.