We introduce the logical grammar emdebbing (LGE), a model inspired by pregroup grammars and categorial grammars to enable unsupervised inference of lexical categories and syntactic rules from a corpus of text. LGE produces comprehensible output summarizing its inferences, has a completely transparent process for producing novel sentences, and can learn from as few as a hundred sentences.
@article{arxiv.2304.14590,
title = {A logical word embedding for learning grammar},
author = {Sean Deyo and Veit Elser},
journal= {arXiv preprint arXiv:2304.14590},
year = {2023}
}