Two Local Models for Neural Constituent Parsing
This work addresses syntactic parsing for natural language processing, presenting an incremental improvement by showing that local models can be competitive with non-local methods.
The paper tackles the problem of syntactic constituent parsing by investigating two simple local neural models that make decisions on constituent spans and CFG rules, achieving labeled bracketing F1 scores of 92.4% on PTB and 87.3% on CTB 5.1.
Non-local features have been exploited by syntactic parsers for capturing dependencies between sub output structures. Such features have been a key to the success of state-of-the-art statistical parsers. With the rise of deep learning, however, it has been shown that local output decisions can give highly competitive accuracies, thanks to the power of dense neural input representations that embody global syntactic information. We investigate two conceptually simple local neural models for constituent parsing, which make local decisions to constituent spans and CFG rules, respectively. Consistent with previous findings along the line, our best model gives highly competitive results, achieving the labeled bracketing F1 scores of 92.4% on PTB and 87.3% on CTB 5.1.