TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Constituency Parsing	Penn Treebank	NFC + BERT-large	F1 score	95.92	# 6

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/investigating-non-local-features-for-neural/constituency-parsing-on-penn-treebank)](https://paperswithcode.com/sota/constituency-parsing-on-penn-treebank?p=investigating-non-local-features-for-neural)`

Investigating Non-local Features for Neural Constituency Parsing

ACL 2022 · Leyang Cui, Sen yang, Yue Zhang ·

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.