Overview of the ICASSP 2023 General Meeting Understanding and Generation Challenge (MUG)
This work addresses the problem of enhancing meeting information processing for users in spoken language applications, but it is incremental as it builds on existing challenge frameworks and datasets.
The paper introduces the ICASSP 2023 MUG Challenge, which aims to advance spoken language processing research by focusing on meeting transcripts to improve information extraction efficiency, and it releases the AliMeeting4MUG Corpus as a large-scale dataset to support this effort.
ICASSP2023 General Meeting Understanding and Generation Challenge (MUG) focuses on prompting a wide range of spoken language processing (SLP) research on meeting transcripts, as SLP applications are critical to improve users' efficiency in grasping important information in meetings. MUG includes five tracks, including topic segmentation, topic-level and session-level extractive summarization, topic title generation, keyphrase extraction, and action item detection. To facilitate MUG, we construct and release a large-scale meeting dataset, the AliMeeting4MUG Corpus.