Quootstrap: Scalable Unsupervised Extraction of Quotation-Speaker Pairs from Large News Corpora via Bootstrapping.
Dario PavlloTiziano PiccardiRobert WestPublished in: CoRR (2018)
Keyphrases
- completely unsupervised
- information extraction
- unsupervised learning
- natural language processing
- unsupervised methods
- speech recognition
- automatic extraction
- social media
- pairwise
- weakly supervised
- data driven
- news corpus
- supervised learning
- relation extraction
- unsupervised manner
- broadcast news
- speaker diarization
- news video
- story segmentation
- news stories
- text data
- semi supervised
- keywords
- machine learning
- news pages
- automatic speech recognition
- news articles
- search engine
- information retrieval