Efficient Constituency Parsing by Pointing
This provides an efficient parsing solution for NLP applications, with incremental improvements in speed and competitive accuracy.
The paper tackles constituency parsing by reformulating it as a series of pointing tasks, achieving 92.78 F1 on English Penn Treebank without pre-trained models and 95.48 F1 with BERT, while being faster than state-of-the-art methods.
We propose a novel constituency parsing model that casts the parsing problem into a series of pointing tasks. Specifically, our model estimates the likelihood of a span being a legitimate tree constituent via the pointing score corresponding to the boundary words of the span. Our parsing model supports efficient top-down decoding and our learning objective is able to enforce structural consistency without resorting to the expensive CKY inference. The experiments on the standard English Penn Treebank parsing task show that our method achieves 92.78 F1 without using pre-trained models, which is higher than all the existing methods with similar time complexity. Using pre-trained BERT, our model achieves 95.48 F1, which is competitive with the state-of-the-art while being faster. Our approach also establishes new state-of-the-art in Basque and Swedish in the SPMRL shared tasks on multilingual constituency parsing.