A Systematic Study of Compositional Syntactic Transformer Language Models

ACL ARR 2025 February Submission3849 Authors

Abstract: Syntactic language models (SLMs) enhance Transformers by incorporating syntactic biases through the modeling of linearized syntactic parse trees alongside surface sentences. This paper focuses on compositional SLMs that are based on constituency parse trees and contain explicit bottom-up composition of constituent representations. We identify key aspects of design choices in existing compositional SLMs and propose a unified framework encompassing both existing models and novel variants. We conduct a comprehensive empirical evaluation of all the variants in our framework across language modeling, syntactic generalization, summarization, and inference efficiency. Based on the experimental results, we make multiple recommendations on the design of compositional SLMs. Our code will be publicly available upon acceptance of the paper.

Paper Type: Long

Research Area: Syntax: Tagging, Chunking and Parsing

Research Area Keywords: constituency parsing, grammar and knowledge-based approaches

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 3849