2020/07/06 by Yoïchi Ishibashi, Yoichi Ishibashi, Katsuhito Sudoh +6
Computer Science · #Analogy #Artificial intelligence #Computation and Language (cs.CL) #Computer science #FOS: Computer and information sciences #Linguistics #Natural Language Processing Techniques #Natural language processing #Philosophy #Queen (butterfly) #Reflection (computer programming) #Speech Recognition and Synthesis #Topic Modeling #Transfer (computing) #Transfer of learning #Word (group theory) #cs.CL
paper · pdf · doi:10.48550/arxiv.2007.02598
published in arXiv (Cornell University) (Cornell University) · Accepted at ACL 2020 Student Research Workshop (SRW)
openalex publication_date 2020/07/06 · arxiv created 2020/07/07 · arxiv updated 2020/07/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Word embeddings, which often represent such analogic relations as king - man + woman = queen, can be used to change a word's attribute, including its gender. For transferring king into queen in this analogy-based manner, we subtract a difference vector man - woman based on the knowledge that king is male. However, developing such knowledge is very costly for words and attributes. In this work, we propose a novel method for word attribute transfer based on reflection mappings without such an analogy operation. Experimental results show that our proposed method can transfer the word attributes of the given words without changing the words that do not have the target attributes.