Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization
| Autor: | Wensi Ding, Zekun Zhang, Polykarpos Meladianos, Antoine J.-P. Tixier, Guokan Shang, Jean-Pierre Lorré, Michalis Vazirgiannis |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Submodular maximization Sentence compression Computer Science - Computation and Language 020205 medical informatics Computer science business.industry 02 engineering and technology computer.software_genre Automatic summarization 0202 electrical engineering electronic engineering information engineering Graph (abstract data type) Leverage (statistics) Semantic memory 020201 artificial intelligence & image processing Artificial intelligence business computer Computation and Language (cs.CL) Natural language processing |
| Zdroj: | Scopus-Elsevier ACL (1) |
| Popis: | We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations. Our work combines the strengths of multiple recent approaches while addressing their weaknesses. Moreover, we leverage recent advances in word embeddings and graph degeneracy applied to NLP to take exterior semantic knowledge into account, and to design custom diversity and informativeness measures. Experiments on the AMI and ICSI corpus show that our system improves on the state-of-the-art. Code and data are publicly available, and our system can be interactively tested. Published as a long paper at ACL 2018. v2: updated Figure 3 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|