Semi-automatic Summarization of Spoken Discourse for Recording Ideas using GPT-3
DOI:
https://doi.org/10.52731/liir.v003.070Keywords:
Discussion support, spoken discourse, GPT-3, summarization, paraphraseAbstract
Although sticky notes are generally used to record and structure ideas stated in a face-to-face workshop, participants sometimes forget to write down their stated ideas due to the inconvenience. This study aims to apply speech recognition to record the ideas stated in a face-to-face workshop using a model created by fine-tuning the GPT-3 to choose the utterances to be recorded and then paraphrase spoken utterances. In the evaluation experiment, we compared the effects of including preceding and following utterances in addition to the summarizing and paraphrasing target utterance, and demonstrated that including only preceding utterances in addition to the summarizing and paraphrasing target utterance in the model input resulted in an F1 value over 0.8 for the selection of utterances to be recorded and ROUGE-1 up to 0.48 for paraphrasing utterance content.References
Miro, https://miro.com/online-whiteboard/, 25 August 2022.
Koiti Hasida“Decentralized, Collaborative, and Diagrammatic Authoring,”, the 3rd International Workshop on Argument for Agreement and Assurance, 2017.
Shun Shiramatsu, Yasunobu Igarashi, “A Preliminary Consideration toward Evidencebased Consensus Building through Human-Agent Collaboration on Semantic Authoring Platform,” , Proceedings of the 15th International Conference on Knowledge, Information and Creativity Support System, 2020, pp. 122-125.
Song, Y., Jiang, D., Zhao, X., Huang, X., Xu, Q., Wong, R.C., and Yang, Q. ,“ SmartMeeting: Automatic Meeting Transcription and Summarization for In-Person Conversations.”, Proc. the 29th ACM International Conference on Multimedia., 2021, pp 27772779
Koay, J.J., Roustai, A., Dai, X., and Liu, F. , “ A Sliding-Window Approach to Automatic Creation of Meeting Minutes.”, arXiv, preprint, 26 April 2021, arXiv:2104.12324.
Ganesh, Prakhar and Saket Dingliwal, “ Abstractive Summarization of Spoken and Written Conversation. ”arXiv, preprint, 5 February 2019, arXiv:1902.01615.
Gen Sato, Shun Shiramatsu, Yuki Yoshimura, Tomoko Omori, Takeshi Mizumoto,“ Applicability of Automatic Selection Mechanism for Speech Recognition Results using GPT-3 to Face-to-face Discussion among Elementary Students, Special Interest Group on Crowd Co-creative Intelligence ”, Vol.2022, No.CCI-009, 2022, pp. 5-8,
Speech to text, https://azure.microsoft.com/en-us/services/cognitive-services/speechto-text/, 25 August 2022.
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, Dario Amodei, “Language models are few-shot learners.” , arXiv, preprint, ,28 May 2020, arXiv:2005.14165.
Lin, Chin-Yew, and Eduard Hovy, “Automatic evaluation of summaries using n-gram co-occurrence statistics.”, Proceedings of the 2003 human language technology conference of the North American chapter of the association for computational linguistics, 2003, pp.150-157.
