It has become a promising direction to measure similarity of Web search queries by mining the increasing amount of click-through data logged by Web search engines, which record the interactions between users and the search engines. Most existing approaches employ the click-through data for similarity measure of queries with little consideration of the temporal factor, while the click-through data is often dynamic and contains rich temporal information. In this paper we present a new framework of time-dependent query semantic similarity model on exploiting the temporal characteristics of historical click-through data. The intuition is that more accurate semantic similarity values between queries can be obtained by taking into account the timestamps of the log data. With a set of user-defined calendar schema and calendar patterns, our time-dependent query similarity model is constructed using the marginalized kernel technique, which can exploit both explicit similarity and implicit semantics from the click-through data effectively. Experimental results on a large set of click-through data acquired from a commercial search engine show that our time-dependent query similarity model is more accurate than the existing approaches. Moreover, we observe that our time-dependent query similarity model can, to some extent, reflect real-world semantics such as real-world events that are happening over time.
%0 Conference Paper
%1 zhao2006timedependent
%A Zhao, Qiankun
%A Hoi, Steven C. H.
%A Liu, Tie-Yan
%A Bhowmick, Sourav S.
%A Lyu, Michael R.
%A Ma, Wei-Ying
%B WWW '06: Proceedings of the 15th international conference on World Wide Web
%C New York, NY, USA
%D 2006
%I ACM
%K click learning-to-rank ranking search similarity web
%P 543--552
%R 10.1145/1135777.1135858
%T Time-dependent semantic similarity measure of queries using historical click-through data
%U http://portal.acm.org/citation.cfm?id=1135777.1135858
%X It has become a promising direction to measure similarity of Web search queries by mining the increasing amount of click-through data logged by Web search engines, which record the interactions between users and the search engines. Most existing approaches employ the click-through data for similarity measure of queries with little consideration of the temporal factor, while the click-through data is often dynamic and contains rich temporal information. In this paper we present a new framework of time-dependent query semantic similarity model on exploiting the temporal characteristics of historical click-through data. The intuition is that more accurate semantic similarity values between queries can be obtained by taking into account the timestamps of the log data. With a set of user-defined calendar schema and calendar patterns, our time-dependent query similarity model is constructed using the marginalized kernel technique, which can exploit both explicit similarity and implicit semantics from the click-through data effectively. Experimental results on a large set of click-through data acquired from a commercial search engine show that our time-dependent query similarity model is more accurate than the existing approaches. Moreover, we observe that our time-dependent query similarity model can, to some extent, reflect real-world semantics such as real-world events that are happening over time.
%@ 1-59593-323-9
@inproceedings{zhao2006timedependent,
abstract = {It has become a promising direction to measure similarity of Web search queries by mining the increasing amount of click-through data logged by Web search engines, which record the interactions between users and the search engines. Most existing approaches employ the click-through data for similarity measure of queries with little consideration of the temporal factor, while the click-through data is often dynamic and contains rich temporal information. In this paper we present a new framework of time-dependent query semantic similarity model on exploiting the temporal characteristics of historical click-through data. The intuition is that more accurate semantic similarity values between queries can be obtained by taking into account the timestamps of the log data. With a set of user-defined calendar schema and calendar patterns, our time-dependent query similarity model is constructed using the marginalized kernel technique, which can exploit both explicit similarity and implicit semantics from the click-through data effectively. Experimental results on a large set of click-through data acquired from a commercial search engine show that our time-dependent query similarity model is more accurate than the existing approaches. Moreover, we observe that our time-dependent query similarity model can, to some extent, reflect real-world semantics such as real-world events that are happening over time.},
added-at = {2010-08-05T09:18:29.000+0200},
address = {New York, NY, USA},
author = {Zhao, Qiankun and Hoi, Steven C. H. and Liu, Tie-Yan and Bhowmick, Sourav S. and Lyu, Michael R. and Ma, Wei-Ying},
biburl = {https://www.bibsonomy.org/bibtex/257cbc64550d3a1b5b8599a0783e95111/jaeschke},
booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web},
doi = {10.1145/1135777.1135858},
interhash = {c765e101c37f6b530e2c1c59808048d7},
intrahash = {57cbc64550d3a1b5b8599a0783e95111},
isbn = {1-59593-323-9},
keywords = {click learning-to-rank ranking search similarity web},
location = {Edinburgh, Scotland},
pages = {543--552},
publisher = {ACM},
timestamp = {2014-07-28T15:57:31.000+0200},
title = {Time-dependent semantic similarity measure of queries using historical click-through data},
url = {http://portal.acm.org/citation.cfm?id=1135777.1135858},
year = 2006
}