Leveraging Grammar Induction for Language Understanding and Generation

TL;DR

This paper presents an unsupervised grammar induction approach that enhances language understanding and generation by integrating induced syntactic structures into Transformer models, improving performance on translation and understanding tasks.

Contribution

Introduces a novel unsupervised grammar induction method that incorporates syntactic structures into Transformer models without needing additional annotations.

Findings

Outperforms original Transformer on multiple tasks

Effective in both from-scratch and pre-trained scenarios

Highlights the benefit of explicit grammatical modeling

Abstract

Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar induction method for language understanding and generation. We construct a grammar parser to induce constituency structures and dependency relations, which is simultaneously trained on downstream tasks without additional syntax annotations. The induced grammar features are subsequently incorporated into Transformer as a syntactic mask to guide self-attention. We evaluate and apply our method to multiple machine translation tasks and natural language understanding tasks. Our method demonstrates superior performance compared to the original Transformer and other models enhanced with external parsers. Experimental results indicate that our method is effective in both from-scratch and pre-trained scenarios. Additionally, our research highlights the contribution of explicitly modeling the grammatical structure of texts to neural network models.