Skip to main navigation menu Skip to main content Skip to site footer

Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale

Abstract

We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are implemented through a special attention mask and deterministic transformation of the linearized tree. We find that TGs outperform various strong baselines on sentence-level language modeling perplexity, as well as on multiple syntax-sensitive language modeling evaluation metrics. Additionally, we find that the recursive syntactic composition bottleneck which represents each sentence as a single vector harms perplexity on document-level language modeling, providing evidence that a different kind of memory mechanism---one that is independent of composed syntactic representations---plays an important role in current successful models of long text.
Presented at EMNLP 2022 Article at MIT Press