Abstract
New Event Detection (NED) aims to recognize the first story for a new event that had not been discussed before. The traditional event detection model basically adopts incremental TF-IDF weights for the terms, not considered the effect of part of speech and named entities in the document. The paper explore the application of weighting the part of speech and generates document theme terms based on the document named entity to detect new event, which can improve performance comparing with the traditional model.KeywordsNew Event DetectionPart of SpeechNamed Entity
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Paper version not known
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
