A Lite Hierarchical Model for Dialogue Summarization with Multi-Granularity Decoder

dc.contributor.author Zheng, Tong
dc.contributor.author Saga, Ryosuke
dc.date.accessioned 2022-12-27T19:02:41Z
dc.date.available 2022-12-27T19:02:41Z
dc.date.issued 2023-01-03
dc.description.abstract Abstract dialogue summarization generation has recently attracted considerable research attention, especially in using hierarchical models to accomplish abstract dialogue summarization tasks successfully. However, problems in recent studies often include an excessive amount of model parameters and long training time mainly because existing dialogue summaries of hierarchical models are typically generated by adding extra encoders and attention layers in the decoder to enhance learning and summarization generation ability of the model. Hence, designing an increasingly lightweight hierarchical model is necessary. A lightweight hierarchical model named ALH-BART is proposed in this study to generate high-accuracy dialogue summaries rapidly. The proposed hierarchical model includes word and turn encoders, which enhance the ability of the model to understand dialogue. A multigranularity decoder in the model is also proposed to decode word- and turn-level information in the decoder at the same time. Encoder parameters in multihead self-attention are provided for each corresponding multihead self-attention to reduce the number of model parameters and improve the speed of model learning effectively. Finally, the effectiveness of the model is verified on SAMSum and DialogSum datasets.
dc.format.extent 10
dc.identifier.doi 10.24251/HICSS.2023.270
dc.identifier.isbn 978-0-9981331-6-4
dc.identifier.uri https://hdl.handle.net/10125/102901
dc.language.iso eng
dc.relation.ispartof Proceedings of the 56th Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject Data Analytics, Data Mining, and Machine Learning for Social Media
dc.subject dialog/chat summarization
dc.subject hierarchical model
dc.subject machine learning
dc.subject social media
dc.title A Lite Hierarchical Model for Dialogue Summarization with Multi-Granularity Decoder
dc.type.dcmi text
prism.startingpage 2180
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
753.61 KB
Adobe Portable Document Format