Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM

TL;DR

This paper revisits the role of semantic graphs, specifically AMR, in syntactic simplification, demonstrating that they can enhance LLM prompting and lead to competitive, interpretable, and generalizable simplification methods.

Contribution

It introduces AMRS$^3$, a new AMR-based method for syntactic simplification, and proposes AMRCoC prompting to improve LLM performance on semantic tasks.

Findings

AMRS$^3$ achieves competitive performance in syntactic simplification.

AMRCoC prompting improves LLM's ability to perform semantic reasoning.

Semantic graphs enhance LLM prompting for syntactic simplification.

Abstract

Symbolic sentence meaning representations, such as AMR (Abstract Meaning Representation) provide expressive and structured semantic graphs that act as intermediates that simplify downstream NLP tasks. However, the instruction-following capability of large language models (LLMs) offers a shortcut to effectively solve NLP tasks, questioning the utility of semantic graphs. Meanwhile, recent work has also shown the difficulty of using meaning representations merely as a helpful auxiliary for LLMs. We revisit the position of semantic graphs in syntactic simplification, the task of simplifying sentence structures while preserving their meaning, which requires semantic understanding, and evaluate it on a new complex and natural dataset. The AMR-based method that we propose, AMRS$^3$, demonstrates that state-of-the-art meaning representations can lead to easy-to-implement simplification methods with competitive performance and unique advantages in cost, interpretability, and generalization. With AMRS$^3$ as an anchor, we discover that syntactic simplification is a task where semantic graphs are helpful in LLM prompting. We propose AMRCoC prompting that guides LLMs to emulate graph algorithms for explicit symbolic reasoning on AMR graphs, and show its potential for improving LLM on semantic-centered tasks like syntactic simplification.