[1T4-OS-32b] OS-32

[1T4-OS-32b-04] Speaker to Dialogue Attribution in Novels by a Large Language Model through Speaker Position Answering Task

〇Shinzan Komata¹, Yuki Zenimoto¹, Takehito Utsuro¹ (1. University of Tsukuba)

Keywords: speaker to dialogue attribution, large language models, novel

The speaker to dialogue attribution task, which identifies the speaker
of an utterance in a novel, is an essential task for the analysis of
novels and their characters. In order to perform this task, it is
necessary to attribute character mentions to utterances. This paper
applies large language models to the task of determining whether the
speaker of the utterance exists in sentences immediately preceding or
subsequent to the utterance, and then divides the entire set of
utterances into two groups. Among these, for the group of utterances
whose speakers are judged to exist in sentences immediately preceding or
subsequent to the utterances, it was shown that the large language
models can perform the task of attributing character mentions to
utterances with higher accuracy compared to the entire set of
utterances.