[1N2] [General Session] 2. Machine Learning

[1N2-03] Learning Style-sensitive Word Vector via Unsupervised-manner

〇Reina Akama¹, Kento Watanabe¹, Sho Yokoi^1,2, Sosuke Kobayashi³, Kentaro Inui^1,2 (1. Tohoku University, 2. RIKEN AIP, 3. Preferred Networks, Inc.)

Keywords:NLP, unsupervised-learning, stylistic variation

This paper is the first study aiming at capturing stylistic similarity in an unsupervised manner.
We construct a novel style-sensitive word vector predicting the target word for giving nearby and wider contexts under the assumption that the style of all the words in an utterance is consistent.
We also introduce an evaluation dataset with human judgments on the stylistic similarity between word pairs.
Experimental results illustrate capturing the stylistic similarity significantly.