Extracting Patterns of Search Queries via Pairwise Coupled
Takuya Konishi(NII), Takuya Ohwa(NII), Sumio Fujita, Kazushi Ikeda(NAIST)), Kohei Hayashi(NII)
WSDM 2016, 2016/2
情報検索 (Information Retrieval)
- A fundamental, yet new, challenge in information retrieval is the identification of patterns in search queries; e.g., to find the query \NY restaurant" is an instance of the pattern \location service." However, because of the diversity of real queries, existing approaches require data preprocessing by humans or limitation of the target query domains, which hinders their applicability. We propose a probabilistic topic model that assumes that each term (e.g.,\NY") has a topic (location). The proposed model recovers a query pattern as a sequence of topics. The key idea is that we consider topic co-occurrence in a query rather than a full combination of topics, which signi?cantly reduces computational cost yet enables us to acquire co- herent topics without preprocessing. Using two real query datasets, we demonstrate that the obtained topics are nat- urally recognizable by humans and are highly accurate in keyword recommendation tasks.
Extracting Patterns of Search Queries via Pairwise Coupled（外部サイト／External Site Link）