Headline Generation using a Training Corpus

  title={Headline Generation using a Training Corpus},
  author={Rong Jin and Alexander G. Hauptmann},
This paper discusses fundamental issues involved in word selection for title generation. We review several common methods that have been used for title generation and compare the performance of those methods using an F1 metric. Both a KNN (k nearest neighbor) method, which we are the first to apply to title generation, and a limited-vocabulary Naïve… CONTINUE READING