Construction and Evaluation of a Self-Attention Model for Semantic Understanding of Sentence-Final Particles
Abstract
Sentence-final particles serve an essential role in spoken Japanese because they express the speaker's mental attitudes toward a proposition and/or an interlocutor. They are acquired at early ages and occur very frequently in everyday conversation. However, there has been little proposal for a computational model of acquiring sentence-final particles. This paper proposes Subjective BERT, a self-attention model that takes various subjective senses in addition to language and images as input and learns the relationship between words and subjective senses. An evaluation experiment revealed that the model understands the usage of "yo", which expresses the speaker's intention to communicate new information, and that of "ne", which denotes the speaker's desire to confirm that some information is shared.
Keywords
Cite
@article{arxiv.2210.00282,
title = {Construction and Evaluation of a Self-Attention Model for Semantic Understanding of Sentence-Final Particles},
author = {Shuhei Mandokoro and Natsuki Oka and Akane Matsushima and Chie Fukada and Yuko Yoshimura and Koji Kawahara and Kazuaki Tanaka},
journal= {arXiv preprint arXiv:2210.00282},
year = {2022}
}
Comments
4 pages, 1 figure. Published in the Program and Abstract Booklet of Workshop on Constructive Approaches to Co-Creative Communication in Joint Conference on Language Evolution, 2022