Constituent Parsing as Sequence Labeling

TL;DR

This paper presents a novel method that transforms constituent parsing into a sequence labeling problem, enabling faster parsing speeds with high accuracy, by encoding tree structures into labels for each word.

Contribution

The authors introduce an injective encoding for constituent trees as sequence labels, extending it to all trees by collapsing unary branches, and demonstrate superior speed and accuracy on benchmark datasets.

Findings

Achieves 90.7% F-score on PTB test set.

Outperforms previous sequence-to-sequence parsers.

Provides the fastest constituent parsing speeds to date.

Abstract

We introduce a method to reduce constituent parsing to sequence labeling. For each word w_t, it generates a label that encodes: (1) the number of ancestors in the tree that the words w_t and w_{t+1} have in common, and (2) the nonterminal symbol at the lowest common ancestor. We first prove that the proposed encoding function is injective for any tree without unary branches. In practice, the approach is made extensible to all constituency trees by collapsing unary branches. We then use the PTB and CTB treebanks as testbeds and propose a set of fast baselines. We achieve 90.7% F-score on the PTB test set, outperforming the Vinyals et al. (2015) sequence-to-sequence parser. In addition, sacrificing some accuracy, our approach achieves the fastest constituent parsing speeds reported to date on PTB by a wide margin.