Investigating Non-local Features for Neural Constituency Parsing
This work addresses parsing accuracy for natural language processing tasks, offering incremental improvements over existing methods.
The paper tackled the problem of improving neural constituency parsing by incorporating non-local features into a local span-based parser, resulting in state-of-the-art BERT-based performance on PTB with 95.92 F1 and strong results on CTB with 92.31 F1.
Thanks to the strong representation power of neural encoders, neural chart-based parsers have achieved highly competitive performance by using local features. Recently, it has been shown that non-local features in CRF structures lead to improvements. In this paper, we investigate injecting non-local features into the training process of a local span-based parser, by predicting constituent n-gram non-local patterns and ensuring consistency between non-local patterns and local constituents. Results show that our simple method gives better results than the self-attentive parser on both PTB and CTB. Besides, our method achieves state-of-the-art BERT-based performance on PTB (95.92 F1) and strong performance on CTB (92.31 F1). Our parser also achieves better or competitive performance in multilingual and zero-shot cross-domain settings compared with the baseline.