作者: Polykarpos Meladianos , Antoine Tixier , Ioannis Nikolentzos , Michalis Vazirgiannis , None
DOI: 10.18653/V1/E17-2074
关键词:
摘要: We introduce a novel method to extract keywords from meeting speech in real-time. Our approach builds on the graph-of-words representation of text and leverages k-core decomposition algorithm properties submodular functions. outperform multiple baselines real-time scenario emulated AMI ICSI corpora. Evaluation is conducted against both extractive abstractive gold standard using two performance metrics newer one based word embeddings.