Concurrent Parsing of Constituency and Dependency
This addresses the need for improved syntactic parsing in natural language processing, offering a novel integration that boosts performance for researchers and practitioners.
The paper tackled the problem of parsing syntactic structure by introducing a model that concurrently parses constituency and dependency, allowing mutual enhancement between parsers. It achieved new state-of-the-art performance on PTB and CTB benchmarks for both tasks.
Constituent and dependency representation for syntactic structure share a lot of linguistic and computational characteristics, this paper thus makes the first attempt by introducing a new model that is capable of parsing constituent and dependency at the same time, so that lets either of the parsers enhance each other. Especially, we evaluate the effect of different shared network components and empirically verify that dependency parsing may be much more beneficial from constituent parsing structure. The proposed parser achieves new state-of-the-art performance for both parsing tasks, constituent and dependency on PTB and CTB benchmarks.