0%

Keyphrase Generation任务综述

任务简介

A keyphrase or keyword is a piece of short, summative content that expresses the main semantic meaning of a longer text. The typical use of a keyphrase or keyword is in scientific publications to provide the core information of a paper.

评价指标

  • F1@5
  • F1@10

数据集

  • KP20K
  • SemEval
  • NUS
  • Krapivin
  • Inspec

SOTA

  • 2019-06-13 Title-Guided Encoding for Keyphrase Generation
Dataset F1@5 F1@10
KP20K 0.372 0.315

相关论文

  • Deep Keyphrase Generation. Rui Meng, Sanqiang Zhao, Shuguang Han, Daqing He, Peter Brusilovsky, Yu Chi. ACL 2017. [pdf] [code]
    Keyphrase Generation的第一篇paper,主要框架是 seq2seq + copy.

  • Semi-Supervised Learning for Neural Keyphrase Generation. Hai Ye, Lu Wang. EMNLP 2018. [pdf]
    解决资源不足问题,提出两个策略:
    (1)微调,通过keyphrase extraction方式人为构造大量数据预训练模型,再通过已有数据微调;
    (2)多任务框架,生成keyphrase的同时生成title。

  • Title-Guided Encoding for Keyphrase Generation. Wang Chen, Yifan Gao, Jiani Zhang, Irwin King, Michael R. Lyu1. AAAI 2019. [pdf]
    本文认为标题包含了文章的主要信息,通过标题来引导摘要的建模已提升模型性能。

  • Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards. Hou Pong Chan, Wang Chen, Lu Wang, Irwin King. ACL 2019. [pdf] [code]

  • Topic-Aware Neural Keyphrase Generation for Social Media Language. Yue Wang. Jing Li, Hou Pong Chan, Irwin King, Michael R. Lyu, Shuming Shi. ACL 2019. [pdf] [code]