A Model of Anaphoric Ambiguities using Sheaf Theoretic Quantum-like Contextuality and BERT
This addresses a key challenge in natural language processing for AI systems, though it is incremental as it builds on existing quantum and NLP methods.
The paper tackled the problem of anaphoric ambiguities in natural language by constructing a schema that exhibits quantum-like contextuality using sheaf theory and BERT embeddings, resulting in the discovery of many sheaf-contextual examples in corpora.
Ambiguities of natural language do not preclude us from using it and context helps in getting ideas across. They, nonetheless, pose a key challenge to the development of competent machines to understand natural language and use it as humans do. Contextuality is an unparalleled phenomenon in quantum mechanics, where different mathematical formalisms have been put forwards to understand and reason about it. In this paper, we construct a schema for anaphoric ambiguities that exhibits quantum-like contextuality. We use a recently developed criterion of sheaf-theoretic contextuality that is applicable to signalling models. We then take advantage of the neural word embedding engine BERT to instantiate the schema to natural language examples and extract probability distributions for the instances. As a result, plenty of sheaf-contextual examples were discovered in the natural language corpora BERT utilises. Our hope is that these examples will pave the way for future research and for finding ways to extend applications of quantum computing to natural language processing.