BSDAR: Beam Search Decoding with Attention Reward in Neural Keyphrase Generation
This addresses decoding problems in keyphrase generation, but it is incremental as it refines existing methods.
The study tackled sequence length bias and beam diversity in neural keyphrase generation by introducing a beam search decoding strategy with word-level and ngram-level rewards, resulting in significant improvements in generating keyphrases present and absent in source text.
This study mainly investigates two common decoding problems in neural keyphrase generation: sequence length bias and beam diversity. To tackle the problems, we introduce a beam search decoding strategy based on word-level and ngram-level reward function to constrain and refine Seq2Seq inference at test time. Results show that our simple proposal can overcome the algorithm bias to shorter and nearly identical sequences, resulting in a significant improvement of the decoding performance on generating keyphrases that are present and absent in source text.