Subspace Representations for Soft Set Operations and Sentence Similarities

arXiv:2210.13034v3 Announce Type: replace-cross
Abstract: In the field of natural language processing (NLP), continuous vector representations are crucial for capturing the semantic meanings of individual words. Yet, when it comes to the representations of sets of words, the conventional vector-based approaches often struggle with expressiveness and lack the essential set operations such as union, intersection, and complement. Inspired by quantum logic, we realize the representation of word sets and corresponding set operations within pre-trained word embedding spaces. By grounding our …

abstract arxiv continuous cs.cl cs.lg language language processing natural natural language natural language processing nlp operations processing semantic set struggle type vector words