Construction and Evaluation of a Self-Attention Model for Semantic Understanding of Sentence-Final Particles
This work addresses a specific problem in natural language processing for Japanese language understanding, but it is incremental as it adapts existing self-attention methods to a new linguistic domain.
The paper tackled the lack of computational models for acquiring Japanese sentence-final particles by proposing Subjective BERT, a self-attention model that learns from language, images, and subjective senses, and it demonstrated the model's ability to understand the usage of particles 'yo' and 'ne' in evaluation experiments.
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.