基于句子选择的关键短语生成  

Neural Keyphrase Generation with Sentence Selective Network

作　　者：罗益超 李争彦 张奇[1] LUO Yichao;LI Zhengyan;ZHANG Qi(School of Computer Science,Fudan University,Shanghai 200433,China)

机构地区：[1]复旦大学计算机科学技术学院,上海200433

出　　处：《中文信息学报》2021年第8期64-72,81,共10页Journal of Chinese Information Processing

基　　金：国家重点研发计划(2017YFB1002104)

摘　　要：关键短语生成是一个能从长文档或者文献中捕获中心思想的实用任务。先前的神经关键短语生成方法基本只注重词级别的信息而忽略文档结构。该文提出了一个句级选择网络(sentence selective network,SenSeNet)用于关键短语生成。该模型重点关注文档的句子结构信息,通过学习句子隐式表示来判断其是否有可能生成关键短语,然后根据判断结果引入对应归纳偏置来辅助解码器生成关键短语。该文使用直通估计量(straight-through estimator)来端到端地训练模型。为了提高句级选择网络性能,该文还提出了一个任务强相关的弱监督信息。实验表明,模型成功地捕获了文档信息,并合理选择了相对较重要的句子,而且模型也更倾向于从这些重要句子中生成关键短语。该文将模型引入到绝大多数序列到序列模型中,在五个数据集中的两个评价指标下,均有显著的性能提升。Keyphrase Generation(KG)is the task of capturing themes from a document,revealing the key information necessary to understand the content.Existing neural keyphrase generation approaches focus only on the token-level information while ignore sentence-level information such as document structure.In this paper,we incorporate the sentence-level inductive bias into KG and propose a new method named Sentence Selective Network(SenSeNet),which can automatically learn the sentence-level information and determine whether the sentence more likely to generate the keyphrase.We use straight-through estimator to train the model in an end-to-end manner and incorporate a weakly-supervised setting which is helpful for the training of the sentence selection module.Experiments show that our model successfully captures the document structure and reasonably distinguishes the significance of sentences,and consistent improvements achieved on two metrics in five datasets.

关 键 词：关键短语生成 文档结构 直通估计量 弱监督 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]