Effective Representation for Easy-First Dependency Parsing

TL;DR

This paper introduces a bottom-up subtree encoding method using child-sum tree-LSTM to enhance easy-first dependency parsing, achieving improved results by leveraging effective subtree representations and pre-trained language models.

Contribution

It proposes a novel subtree encoding technique based on child-sum tree-LSTM that improves easy-first dependency parsing performance.

Findings

Effective subtree encoder promotes parsing process

Achieves promising results on benchmark treebanks

Further improves results with pre-trained language models

Abstract

Easy-first parsing relies on subtree re-ranking to build the complete parse tree. Whereas the intermediate state of parsing processing is represented by various subtrees, whose internal structural information is the key lead for later parsing action decisions, we explore a better representation for such subtrees. In detail, this work introduces a bottom-up subtree encoding method based on the child-sum tree-LSTM. Starting from an easy-first dependency parser without other handcraft features, we show that the effective subtree encoder does promote the parsing process, and can make a greedy search easy-first parser achieve promising results on benchmark treebanks compared to state-of-the-art baselines. Furthermore, with the help of the current pre-training language model, we further improve the state-of-the-art results of the easy-first approach.