カンファレンス (国際) Selectively Expanding Queries and Documents for News Background Linking

Lirong Zhang (Tsukuba univ.), Hideo Joho (Tsukuba univ.), Sumio Fujita, Hai-Tao Yu (Tsukuba univ.)

31st ACM International Conference on Information and Knowledge Management (CIKM 2022)


Background articles are crucial for readers to grasp the context of news stories fully. However, existing approaches of background article search tend to apply a single ranking method to all types of search topics. In this paper, we focused on an important type of search topics on news articles: time-sensitive and non-time-sensitive. To verify whether or not these two types of search topics can benefit from different retrieving methods, we examined a set of techniques such as document expansion, query rewriting, and semantic reranking. Moreover, the relationship between background articles and topics is verified by the two strategies of document expansion (specificity and diversity). The experiment with TREC 2021 News Track test collection demonstrates that optimal use of these techniques is indeed different between the two types of search topics. Furthermore, when the two methods are combined properly, it can significantly improve the performance of the background linking task. Finally, our in-depth analysis of topics and search results indicates that time-sensitive topics benefit from background articles that can provide more specific knowledge, while non-time-sensitive topics benefit from diversified retrieved documents.

Paper : Selectively Expanding Queries and Documents for News Background Linking (外部サイト)