Personalized News Headline Generation System with Fine-grained User Modeling

2022 18th International Conference on Mobility, Sensing and Networking (MSN) Pub Date : 2022-12-01 DOI:10.1109/MSN57253.2022.00097

Jiaohong Yao

{"title":"Personalized News Headline Generation System with Fine-grained User Modeling","authors":"Jiaohong Yao","doi":"10.1109/MSN57253.2022.00097","DOIUrl":null,"url":null,"abstract":"Personalized news headline generation aims to sum-marize a news article as a news headline, according to the preference of a specific user. It can help users filter their interested news quickly and increase the news click rates for news providers. However, in this field, when learning user interests from their historically clicked news, existing research only learned user interests on word and news level, ignoring sentence level informativeness. This paper proposes a user model, adding sentence-level informativeness to learn user interests, and further guide the news headline generation. To be more detailed, based on attention layers, sentence and news are represented as the weighted sum of word and sentence representations, respectively. To further explore the correlation between different news contents (news title, body, and topic information), the query vectors in the attention layers are replaced by news content. Experiments on the dataset PENS show that the performance of these two models is better than the baseline model on the evaluation metrics ROUGE. Finally, some future directions are discussed, including interactions across informativeness levels and contents.","PeriodicalId":114459,"journal":{"name":"2022 18th International Conference on Mobility, Sensing and Networking (MSN)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 18th International Conference on Mobility, Sensing and Networking (MSN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MSN57253.2022.00097","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Personalized news headline generation aims to sum-marize a news article as a news headline, according to the preference of a specific user. It can help users filter their interested news quickly and increase the news click rates for news providers. However, in this field, when learning user interests from their historically clicked news, existing research only learned user interests on word and news level, ignoring sentence level informativeness. This paper proposes a user model, adding sentence-level informativeness to learn user interests, and further guide the news headline generation. To be more detailed, based on attention layers, sentence and news are represented as the weighted sum of word and sentence representations, respectively. To further explore the correlation between different news contents (news title, body, and topic information), the query vectors in the attention layers are replaced by news content. Experiments on the dataset PENS show that the performance of these two models is better than the baseline model on the evaluation metrics ROUGE. Finally, some future directions are discussed, including interactions across informativeness levels and contents.

查看原文本刊更多论文

具有细粒度用户建模的个性化新闻标题生成系统

个性化新闻标题生成旨在根据特定用户的偏好，将一篇新闻文章总结为新闻标题。它可以帮助用户快速过滤他们感兴趣的新闻，并提高新闻提供商的新闻点击率。然而，在这一领域中，现有的研究在从用户的历史点击新闻中学习用户兴趣时，只学习了单词和新闻层面的用户兴趣，忽略了句子层面的信息性。本文提出了一个用户模型，通过增加句子级的信息量来学习用户兴趣，进一步指导新闻标题的生成。更详细地说，基于注意层，句子和新闻分别被表示为单词和句子表示的加权和。为了进一步探索不同新闻内容(新闻标题、新闻正文、新闻主题信息)之间的相关性，将关注层中的查询向量替换为新闻内容。在数据集PENS上的实验表明，这两种模型在评价指标ROUGE上的性能优于基线模型。最后，讨论了未来的发展方向，包括信息水平和内容之间的相互作用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2022 18th International Conference on Mobility, Sensing and Networking (MSN)

自引率

0.00%

发文量