Reflection-based Word Attribute Transfer
This addresses a domain-specific challenge in natural language processing for researchers and practitioners by offering a more efficient approach to word attribute manipulation.
The paper tackles the problem of costly knowledge development for word attribute transfer by proposing a reflection-based method that avoids analogy operations, achieving attribute transfer without altering non-target words.
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.