Rule Augmented Unsupervised Constituency Parsing

TL;DR

This paper introduces a rule-augmented approach to unsupervised constituency parsing that incorporates linguistic grammar rules, leading to improved syntactic structure learning and state-of-the-art results on benchmark datasets.

Contribution

It presents a novel method that integrates syntactic grammar rules into unsupervised parsing models, enhancing their ability to learn accurate syntactic structures.

Findings

Achieved new state-of-the-art results on MNLI and WSJ datasets.

Demonstrated that incorporating linguistic rules improves unsupervised parsing accuracy.

The approach is independent of the base parsing system.

Abstract

Recently, unsupervised parsing of syntactic trees has gained considerable attention. A prototypical approach to such unsupervised parsing employs reinforcement learning and auto-encoders. However, no mechanism ensures that the learnt model leverages the well-understood language grammar. We propose an approach that utilizes very generic linguistic knowledge of the language present in the form of syntactic rules, thus inducing better syntactic structures. We introduce a novel formulation that takes advantage of the syntactic grammar rules and is independent of the base system. We achieve new state-of-the-art results on two benchmarks datasets, MNLI and WSJ. The source code of the paper is available at https://github.com/anshuln/Diora_with_rules.