Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generation

With the rapid proliferation of online media sources and published news, headlines have become increasingly important for attracting readers to news articles, since users may be overwhelmed with the massive information. In this paper, we generate inspired headlines that preserve the nature of news articles and catch the eye of the reader simultaneously. The task of inspired headline generation can be viewed as a specific form of Headline Generation (HG) task, with the emphasis on creating an attractive headline from a given news article. To generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG). PORL-HG exploits the extractive-abstractive architecture with 1) Popular Topic Attention (PTA) for guiding the extractor to select the attractive sentence from the article and 2) a popularity predictor for guiding the abstractor to rewrite the attractive sentence. Moreover, since the sentence selection of the extractor is not differentiable, techniques of reinforcement learning (RL) are utilized to bridge the gap with rewards obtained from a popularity score predictor. Through quantitative and qualitative experiments, we show that the proposed PORL-HG significantly outperforms the state-of-the-art headline generation models in terms of attractiveness evaluated by both human (71.03%) and the predictor (at least 27.60%), while the faithfulness of PORL-HG is also comparable to the state-of-the-art generation model.

[1]  Bowen Zhou,et al.  Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond , 2016, CoNLL.

[2]  Jun Xu,et al.  Question Headline Generation for News Articles , 2018, CIKM.

[3]  Jason Weston,et al.  A Neural Attention Model for Abstractive Sentence Summarization , 2015, EMNLP.

[4]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[5]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[6]  Dirk Hovy,et al.  Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning , 2018, EMNLP.

[7]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[8]  Lukasz Kaiser,et al.  Sentence Compression by Deletion with LSTMs , 2015, EMNLP.

[9]  Sung-Shun Weng,et al.  Recommendation on Keyword Combination of News Headlines , 2018, 2018 5th International Conference on Systems and Informatics (ICSAI).

[10]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[11]  Mirella Lapata,et al.  Ranking Sentences for Extractive Summarization with Reinforcement Learning , 2018, NAACL.

[12]  Naoaki Okazaki,et al.  Neural Headline Generation on Abstract Meaning Representation , 2016, EMNLP.

[13]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

[14]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[15]  Hidekazu Yanagimoto,et al.  Headline Generation with Recurrent Neural Network , 2018 .

[16]  Daniel Marcu,et al.  Statistics-Based Summarization - Step One: Sentence Compression , 2000, AAAI/IAAI.

[17]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[18]  Mirella Lapata,et al.  Sentence Compression Beyond Word Deletion , 2008, COLING.

[19]  Mark T. Keane,et al.  Helping News Editors Write Better Headlines: A Recommender to Improve the Keyword Contents & Shareability of News Headlines , 2016, IJCAI 2016.

[20]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[21]  Hayato Kobayashi,et al.  Extractive Headline Generation Based on Learning to Rank for Community Question Answering , 2018, COLING.

[22]  Yen-Chun Chen,et al.  Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting , 2018, ACL.

[23]  Anne Schuth,et al.  Effective Headlines of Newspaper Articles in a Digital Environment , 2017 .

[24]  Mirella Lapata,et al.  Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization , 2018, EMNLP.

[25]  Bowen Zhou,et al.  SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents , 2016, AAAI.

[26]  Paul Over,et al.  DUC in context , 2007, Inf. Process. Manag..

[27]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[28]  Mirella Lapata,et al.  Neural Summarization by Extracting Sentences and Words , 2016, ACL.