[1P4-GS-6] Language media processing: basic theory

[1P4-GS-6-02] Subspace-based Set Operations on a Pre-trained Word Embedding Space

〇Yoichi Ishibashi¹, Sho Yokoi^2,3, Katsuhito Sudoh^1,3,4, Satoshi Nakamura^1,3 (1. Nara Institute of Science and Technology, 2. Tohoku University, 3. Center for Advanced Intelligence Project, RIKEN, 4. PRESTO, Japan Science and Technology Agency)

[[Online]]

Keywords:word embedding, set, representation learning

Word embedding is a fundamental technology in natural language processing. Representation learning for words has been progressing; however, word set operations in embedding spaces have not been defined yet, although they are often performed on sets of words. In this study, we aim to compute representations of sets and set operations using only pre-trained word embeddings. We focused on quantum logic and demonstrated that quantum logic can function as a linguistic set operation in the embedding space.