Encoder-Decoder Shift-Reduce Syntactic Parsing

TL;DR

This paper explores the application of encoder-decoder neural networks to transition-based syntactic parsing, achieving competitive results on dependency and constituent parsing tasks.

Contribution

It is the first empirical study applying encoder-decoder models to transition-based parsing, demonstrating their effectiveness in this context.

Findings

Achieved comparable results to state-of-the-art dependency parsers.

Outperformed existing encoder-decoder models on constituent parsing.

Showed encoder-decoder models are viable for transition-based parsing.

Abstract

Starting from NMT, encoder-decoder neu- ral networks have been used for many NLP problems. Graph-based models and transition-based models borrowing the en- coder components achieve state-of-the-art performance on dependency parsing and constituent parsing, respectively. How- ever, there has not been work empirically studying the encoder-decoder neural net- works for transition-based parsing. We apply a simple encoder-decoder to this end, achieving comparable results to the parser of Dyer et al. (2015) on standard de- pendency parsing, and outperforming the parser of Vinyals et al. (2015) on con- stituent parsing.