Exploring Methods for Predicting Important Utterances Contributing to Meeting Summarization

Multimodal Technologies and Interaction

Fumio Nihei¹  YukikoI. Nakano¹ 

[1] Faculty of Science and Technology, Seikei University, 3-3-1, Kichijoji Kitamachi, Musashino Shi, Tokyo 180-8633, Japan;

关键词: important utterances contributing to the meeting summary;    meeting summarization;    multimodal multiparty interaction;    handcrafted feature;    deep neural network;    meeting browser;   

DOI  :  10.3390/mti3030050

来源: DOAJ

【 摘 要 】

Meeting minutes are useful, but creating meeting summaries are a time consuming task. Aiming at supporting such task, this paper proposes prediction models for important utterances that should be included in the meeting summary by using multimodal and multiparty features. We will tackle this issue from two approaches: Handcrafted feature models and deep neural network models. The best handcrafted feature model achieved 0.707 in F-measure, and the best deep-learning based verbal and nonverbal model (V-NV model) achieved 0.827 in F-measure. Based on the V-NV model, we implemented a meeting browser, and conducted a user study. The results showed that the proposed meeting browser better contributes to the understanding of the content of the discussion and the participant roles in the discussion than the conventional text-based browser.

【 授权许可】

Unknown