arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09485cs.CLcs.LGstat.ML
收藏

BSDAR:神经关键短语生成中基于注意力奖励的束搜索解码

BSDAR: Beam Search Decoding with Attention Reward in Neural Keyphrase Generation

Eindhoven University of Technology(埃因霍温理工大学);BRIN Indonesia(印度尼西亚国家研究与创新署)

Iftitahu Ni'mah, Vlado Menkovski, Mykola Pechenizkiy

AI总结:

本文针对神经关键短语生成中的长度偏差和束多样性问题,提出基于词级与n-gram级奖励函数的束搜索解码策略BSDAR,有效提升关键短语生成质量。

摘要:

本研究主要探讨神经关键短语生成中两个常见的解码问题:序列长度偏差和束多样性不足。为解决这些问题,我们提出了一种基于词级和n-gram级奖励函数的束搜索解码策略,在测试阶段约束并优化Seq2Seq推理。实验结果表明,这一简单方案能够克服算法对较短且几乎相同序列的偏差,显著提升了解码性能,在生成源文本中存在和不存在的关键短语方面均取得改善。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑