Deep Keyphrase Generation

generate keyphrases from abstract using seq2seq by Rui Meng for ACL

Abstract

• background: Keyphrase provides highly summative information that can be effectively used for understanding, organizing and retrieving text content.
• drawback: These approaches can neither identify keyphrases that do not appear in the text, nor capture the real semantic meaning behind the text.
• in this work:
  • encoder-decoder(seq2seq) framework named deep keyphrase generation.
  • Empirical analysis on six datasets demonstrates that our proposed model not only achieves a significant performance boost on extracting keyphrases that appear absent keyphrases based on the semantic meaning of the text.