Multitask Pointer Network for multi-representational parsing

Daniel Fernández‐González

doi:10.1016/j.knosys.2021.107760

2022-01-01

Daniel Fernández‐González *

Carlos Gómez‐Rodríguez

DOI：10.1016/j.knosys.2021.107760

原文链接

查看原文

摘要

En 中文

Dependency and constituent trees are widely used by many artificial intelligence applications for representing the syntactic structure of human languages. Typically, these structures are separately produced by either dependency or constituent parsers. In this article, 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. (C) 2021 The Authors. Published by Elsevier B.V.

Keyword:

Natural language processing

Computational linguistics

Parsing

Dependency parsing

Constituent parsing

Neural network

Deep learning