BSDAR: Beam Search Decoding with Attention Reward in Neural Keyphrase Generation
Computation and Language
2023-10-31 v2 Machine Learning
Machine Learning
Abstract
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.
Cite
@article{arxiv.1909.09485,
title = {BSDAR: Beam Search Decoding with Attention Reward in Neural Keyphrase Generation},
author = {Iftitahu Ni'mah and Vlado Menkovski and Mykola Pechenizkiy},
journal= {arXiv preprint arXiv:1909.09485},
year = {2023}
}
Comments
arxiv preprint. a preliminary study