Rule Augmented Unsupervised Constituency Parsing

by   Atul Sahay, et al.

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


page 1

page 2

page 3

page 4


An Imitation Learning Approach to Unsupervised Parsing

Recently, there has been an increasing interest in unsupervised parsers ...

SMIE: Weakness is Power!: Auto-indentation with incomplete information

Automatic indentation of source code is fundamentally a simple matter of...

Evaluating Induced CCG Parsers on Grounded Semantic Parsing

We compare the effectiveness of four different syntactic CCG parsers for...

Geometry-Aware Supertagging with Heterogeneous Dynamic Convolutions

The syntactic categories of categorial grammar formalisms are structured...

Reinforcement Learning of Minimalist Numeral Grammars

Speech-controlled user interfaces facilitate the operation of devices an...

Unsupervised Learning of Explainable Parse Trees for Improved Generalisation

Recursive neural networks (RvNN) have been shown useful for learning sen...

Unsupervised Sentence Simplification via Dependency Parsing

Text simplification is the task of rewriting a text so that it is readab...

Code Repositories


Code release for the paper Rule Augmented Unsupervised Constituency Parsing to appear in the Findings of ACL 2021

view repo

Please sign up or login with your details

Forgot password? Click here to reset