Reflection-based Word Attribute Transfer

Yoichi Ishibashi, Katsuhito Sudoh, Koichiro Yoshino, Satoshi Nakamura


Abstract
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.
Anthology ID:
2020.acl-srw.8
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
July
Year:
2020
Address:
Online
Editors:
Shruti Rijhwani, Jiangming Liu, Yizhong Wang, Rotem Dror
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
51–58
Language:
URL:
https://aclanthology.org/2020.acl-srw.8
DOI:
10.18653/v1/2020.acl-srw.8
Bibkey:
Cite (ACL):
Yoichi Ishibashi, Katsuhito Sudoh, Koichiro Yoshino, and Satoshi Nakamura. 2020. Reflection-based Word Attribute Transfer. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 51–58, Online. Association for Computational Linguistics.
Cite (Informal):
Reflection-based Word Attribute Transfer (Ishibashi et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-srw.8.pdf
Video:
 http://slideslive.com/38928650
Code
 ahclab/reflection +  additional community code