Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding

Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding
复制标题

通过可扩展的主题嵌入从连续新闻流中无监督地发现故事

DOI:
10.1145/3539618.3591782
复制
发表时间:
2023
期刊:
ACM
影响因子:
--
通讯作者:
Han, Jiawei
Han, Jiawei
中科院分区:
--
文献类型:
--
作者:
Yoon, Susik;Lee, Dongha;Zhang, Yunyi;Han, Jiawei

文献摘要

参考文献

相似文献

实时无监督地发现具有相关新闻文章的故事,可以帮助人们消化大量新闻流,而无需昂贵的人工注释。现有的无监督在线故事发现研究的一个常见方法是用基于符号或图形的嵌入来表示新闻文章,并将它们逐步聚类成故事。最近的大型语言模型有望进一步改进嵌入,但通过不加区别地编码文章中的所有信息来直接采用模型对于处理文本丰富和不断变化的新闻流是无效的。在这项工作中,我们提出了一种新的主题嵌入与现成的预训练的句子编码器动态表示文章和故事,考虑他们的共享时间主题。为了实现无监督的在线故事发现的想法,一个可扩展的框架USTORY介绍了两个主要技术,主题和时间感知的动态嵌入和新颖性感知的自适应聚类,由轻量级的故事摘要。对真实的新闻数据集的全面评估表明,USTORY实现了比基线更高的故事发现性能,同时具有鲁棒性和可扩展性,可用于各种流媒体设置。
Unsupervised discovery of stories with correlated news articles in real-time helps people digest massive news streams without expensive human annotations. A common approach of the existing studies for unsupervised online story discovery is to represent news articles with symbolic- or graph-based embedding and incrementally cluster them into stories. Recent large language models are expected to improve the embedding further, but a straightforward adoption of the models by indiscriminately encoding all information in articles is ineffective to deal with text-rich and evolving news streams. In this work, we propose a novel thematic embedding with an off-the-shelf pretrained sentence encoder to dynamically represent articles and stories by considering their shared temporal themes. To realize the idea for unsupervised online story discovery, a scalable framework USTORY is introduced with two main techniques, theme- and time-aware dynamic embedding and novelty-aware adaptive clustering, fueled by lightweight story summaries. A thorough evaluation with real news data sets demonstrates that USTORY achieves higher story discovery performances than baselines while being robust and scalable to various streaming settings.
DOI: 10.1145/3543507.3583371
发表时间: 2023-02
期刊: Proceedings of the ACM Web Conference 2023
影响因子: --
作者:
Susik Yoon;Hou Pong Chan;Jiawei Han
通讯作者: Susik Yoon;Hou Pong Chan;Jiawei Han
聚合网络新闻源的内部结构
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
M. Trampus;B. Novak
通讯作者: B. Novak
DOI: 10.14778/3407790.3407813
发表时间: 2020-07-01
影响因子: 2.5
作者:
Fritz, Manuel;Behringer, Michael;Schwarz, Holger
通讯作者: Schwarz, Holger
DOI: 10.18653/v1/d18-1483
发表时间: 2018-09
期刊: --
影响因子: --
作者:
Sebastião Miranda;Arturs Znotins;Shay B. Cohen;Guntis Barzdins
通讯作者: Sebastião Miranda;Arturs Znotins;Shay B. Cohen;Guntis Barzdins
更新的方法
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
Fukuzawa;K.;Dannoura;M. and Shibata;H
通讯作者: H