Multitask Pointer Network for Multi-Representational Parsing
This provides a unified parsing solution for computational linguistics that handles multiple syntactic formalisms, though it is incremental in combining existing techniques.
The authors tackled the problem of parsing sentences with both constituent and dependency trees, including discontinuous structures, by developing a multitask Pointer Network with shared encoder and separate decoders. The result was the first parser to jointly produce unrestricted constituent and dependency trees from a single model, achieving state-of-the-art accuracies on benchmarks like English/Chinese Penn Treebanks and German NEGRA/TIGER datasets.
We propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-projective syntactic structures. To that end, we develop a Pointer Network architecture with two separate task-specific decoders and a common encoder, and follow a multitask learning strategy to jointly train them. The resulting quadratic system, not only becomes the first parser that can jointly produce both unrestricted constituent and dependency trees from a single model, but also proves that both syntactic formalisms can benefit from each other during training, achieving state-of-the-art accuracies in several widely-used benchmarks such as the continuous English and Chinese Penn Treebanks, as well as the discontinuous German NEGRA and TIGER datasets.