Integrating Symbolic Natural Language Understanding and Language Models for Word Sense Disambiguation

TL;DR

This paper presents a novel approach combining symbolic natural language understanding with large language models to perform word sense disambiguation without requiring hand-annotated training data, enhancing the ability to handle richer semantic representations.

Contribution

It introduces a method that leverages language models as oracles to disambiguate meanings generated by symbolic NLU systems, eliminating the need for annotated training data.

Findings

Effective disambiguation without training data

Improved handling of richer semantic representations

Comparable to human-annotated gold standards

Abstract

Word sense disambiguation is a fundamental challenge in natural language understanding. Current methods are primarily aimed at coarse-grained representations (e.g. WordNet synsets or FrameNet frames) and require hand-annotated training data to construct. This makes it difficult to automatically disambiguate richer representations (e.g. built on OpenCyc) that are needed for sophisticated inference. We propose a method that uses statistical language models as oracles for disambiguation that does not require any hand-annotation of training data. Instead, the multiple candidate meanings generated by a symbolic NLU system are converted into distinguishable natural language alternatives, which are used to query an LLM to select appropriate interpretations given the linguistic context. The selected meanings are propagated back to the symbolic NLU system. We evaluate our method against human-annotated gold answers to demonstrate its effectiveness.