Construction and Evaluation of a Self-Attention Model for Semantic Understanding of Sentence-Final Particles

TL;DR

This paper introduces Subjective BERT, a self-attention model designed to understand sentence-final particles in Japanese, capturing speaker attitudes and intentions through subjective senses, language, and images.

Contribution

It presents a novel self-attention model that integrates subjective senses for better semantic understanding of Japanese sentence-final particles.

Findings

Model effectively understands 'yo' as indicating new information

Model captures 'ne' as a marker of shared understanding

Demonstrates improved semantic comprehension of 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.