<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2019-clickbait">
    <titleInfo>
        <title>Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Peng</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chien-Sheng</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrea</namePart>
        <namePart type="family">Madotto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pascale</namePart>
        <namePart type="family">Fung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Sensational headlines are headlines that capture people’s attention and generate reader interest. Conventional abstractive headline generation methods, unlike human writers, do not optimize for maximal reader attention. In this paper, we propose a model that generates sensational headlines without labeled data. We first train a sensationalism scorer by classifying online headlines with many comments (“clickbait”) against a baseline of headlines generated from a summarization model. The score from the sensationalism scorer is used as the reward for a reinforcement learner. However, maximizing the noisy sensationalism reward will generate unnatural phrases instead of sensational headlines. To effectively leverage this noisy reward, we propose a novel loss function, Auto-tuned Reinforcement Learning (ARL), to dynamically balance reinforcement learning (RL) with maximum likelihood estimation (MLE). Human evaluation shows that 60.8% of samples generated by our model are sensational, which is significantly better than the Pointer-Gen baseline and other RL models.</abstract>
    <identifier type="citekey">xu-etal-2019-clickbait</identifier>
    <identifier type="doi">10.18653/v1/D19-1303</identifier>
    <location>
        <url>https://aclanthology.org/D19-1303</url>
    </location>
    <part>
        <date>2019-nov</date>
        <extent unit="page">
            <start>3065</start>
            <end>3075</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning
%A Xu, Peng
%A Wu, Chien-Sheng
%A Madotto, Andrea
%A Fung, Pascale
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 nov
%I Association for Computational Linguistics
%C Hong Kong, China
%F xu-etal-2019-clickbait
%X Sensational headlines are headlines that capture people’s attention and generate reader interest. Conventional abstractive headline generation methods, unlike human writers, do not optimize for maximal reader attention. In this paper, we propose a model that generates sensational headlines without labeled data. We first train a sensationalism scorer by classifying online headlines with many comments (“clickbait”) against a baseline of headlines generated from a summarization model. The score from the sensationalism scorer is used as the reward for a reinforcement learner. However, maximizing the noisy sensationalism reward will generate unnatural phrases instead of sensational headlines. To effectively leverage this noisy reward, we propose a novel loss function, Auto-tuned Reinforcement Learning (ARL), to dynamically balance reinforcement learning (RL) with maximum likelihood estimation (MLE). Human evaluation shows that 60.8% of samples generated by our model are sensational, which is significantly better than the Pointer-Gen baseline and other RL models.
%R 10.18653/v1/D19-1303
%U https://aclanthology.org/D19-1303
%U https://doi.org/10.18653/v1/D19-1303
%P 3065-3075

Markdown (Informal)

[Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning](https://aclanthology.org/D19-1303) (Xu et al., EMNLP 2019)

• Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning (Xu et al., EMNLP 2019)

ACL

• Peng Xu, Chien-Sheng Wu, Andrea Madotto, and Pascale Fung. 2019. Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3065–3075, Hong Kong, China. Association for Computational Linguistics.