Letting AI pick the right word meaning—no hand labels needed
Words often have many meanings. Choosing the right one in context—"bank" of a river or a lender?—is a classic AI challenge.
A new approach by Kexin Zhao and Ken Forbus blends symbolic understanding with modern language models. Here’s how it works:
- A symbolic system lists possible meanings for a word.
- Each meaning is rewritten as a clear, natural-language option.
- An LLM is asked which option best fits the sentence.
- The chosen meaning feeds back into the symbolic system for richer reasoning.
Why this matters: It avoids costly hand-labeled training data and goes beyond coarse labels (like WordNet frames) to support deeper knowledge bases (e.g., OpenCyc). In tests against human-annotated answers, the method proved effective.
Paper: Integrating Symbolic Natural Language Understanding and Language Models for Word Sense Disambiguation
Authors: Kexin Zhao, Ken Forbus
Link: https://arxiv.org/abs/2511.16577v1
Paper: https://arxiv.org/abs/2511.16577v1
Register: https://www.AiFeta.com
#AI #NLP #LLM #WordSenseDisambiguation #SymbolicAI #KnowledgeGraphs #NLU #Research
