Rule Augmented Unsupervised Constituency Parsing

05/21/2021
by   Atul Sahay, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/05/2019

An Imitation Learning Approach to Unsupervised Parsing

Recently, there has been an increasing interest in unsupervised parsers ...
06/04/2020

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

Automatic indentation of source code is fundamentally a simple matter of...
09/29/2016

Evaluating Induced CCG Parsers on Grounded Semantic Parsing

We compare the effectiveness of four different syntactic CCG parsers for...
03/23/2022

Geometry-Aware Supertagging with Heterogeneous Dynamic Convolutions

The syntactic categories of categorial grammar formalisms are structured...
06/11/2019

Reinforcement Learning of Minimalist Numeral Grammars

Speech-controlled user interfaces facilitate the operation of devices an...
04/11/2021

Unsupervised Learning of Explainable Parse Trees for Improved Generalisation

Recursive neural networks (RvNN) have been shown useful for learning sen...
06/10/2022

Unsupervised Sentence Simplification via Dependency Parsing

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

Code Repositories

Diora_with_rules

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