Revisiting conversation discourse for dialogue disentanglement

• Main Authors: LI, Bobo, FEI, Hao, LI, Fei, WU, Shengqiong, LIAO, Lizi, WEI, Yinwei, CHUA, Tat-seng, JI, Donghong
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Dialogue disentanglement; Graph neural network; Feature encoding; Model learning; Artificial Intelligence and Robotics; Computer Sciences
• Online Access: https://ink.library.smu.edu.sg/sis_research/9883; https://ink.library.smu.edu.sg/context/sis_research/article/10883/viewcontent/2306.03975v2.pdf
• Institution: Singapore Management University

Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement requires the full understanding and harnessing of the intri...