Michael Völske
ABSTRACT
Several recent task-based search studies aim at splitting query logs into sets of queries for the same task or information need. We address the natural next step: mapping a currently submitted query to an appropriate task in an already task-split log. This query-task mapping can, for instance, enhance query suggestions---rendering efficiency of the mapping, besides accuracy, a key objective. Our main contributions are three large benchmark datasets and preliminary experiments with four query-task mapping approaches: (1) a Trie-based approach, (2) MinHash~LSH, (3) word movers distance in a Word2Vec setup, and (4) an inverted index-based approach. The experiments show that the fast and accurate inverted index-based method forms a strong baseline.
- Ahmed Hassan Awadallah, Ryen W. White, Patrick Pantel, Susan T. Dumais, and Yi-Min Wang. 2014. Supporting complex search tasks. In Proceedings of CIKM 2014, 829--838. Google Scholar
Digital Library
- Mayank Bawa, Tyson Condie, and Prasanna Ganesan. 2005. LSH Forest: Self-tuning indexes for similarity search. In Proceedings of WWW 2005, 651--660. Google ScholarDigital Library
- Paolo Boldi, Francesco Bonchi, Carlos Castillo, Debora Donato, Aristides Gionis, and Sebastiano Vigna. 2008. The query-flow graph: Model and applications. In Proceedings of CIKM 2008, 609--618. Google ScholarDigital Library
- Ben Carterette, Evangelos Kanoulas, Mark M. Hall, and Paul D. Clough. 2014. Overview of the TREC 2014 Session track. In Proceedings of TREC 2014.Google Scholar
- Rene De La Briandais. 1959. File searching using variable length keys. In Proceedings of IRE-AIEE-ACM 1959, 295--298. Google ScholarDigital Library
- Debora Donato, Francesco Bonchi, Tom Chi, and Yoëlle S. Maarek. 2010. Do you want to take notes?: Identifying research missions in Yahoo! search pad. In Proceedings of WWW 2010, 321--330. Google ScholarDigital Library
- Daniel Gayo-Avello. 2009. A survey on session detection methods in query logs and a proposal for future evaluation. Information Sciences, Vol. 179, 12 (2009), 1822--1843. Google ScholarDigital Library
- Matthias Hagen, Jakob Gomoll, Anna Beyer, and Benno Stein. 2013. From search session detection to search mission detection. In Proceedings of OAIR 2013, 85--92. Google ScholarDigital Library
- Matthias Hagen, Martin Potthast, Michael Völske, Jakob Gomoll, and Benno Stein. 2016. How writers search: Analyzing the search and writing logs of non-fictional essays. In Proceedings of CHIIR 2016, 193--202. Google ScholarDigital Library
- Daqing He, Ayse Göker, and David J. Harper. 2002. Combining evidence for automatic web session identification. Information Processing & Management, Vol. 38, 5 (2002), 727--742. Google ScholarDigital Library
- Wen Hua, Yangqiu Song, Haixun Wang, and Xiaofang Zhou. 2013. Identifying users' topical tasks in web search. In Proceedings of WSDM 2013, 93--102. Google ScholarDigital Library
- Bernard J. Jansen, Amanda Spink, Chris Blakely, and Sherry Koshman. 2007. Defining a session on web search engines. JASIST, Vol. 58, 6 (2007), 862--871. Google ScholarDigital Library
- Rosie Jones and Kristina Lisa Klinkner. 2008. Beyond the session timeout: Automatic hierarchical segmentation of search topics in query logs. In Proceedings of CIKM 2008, 699--708. Google ScholarDigital Library
- Evangelos Kanoulas, Emine Yilmaz, Rishabh Mehrotra, Ben Carterette, Nick Craswell, and Peter Bailey. 2017. TREC 2017 Tasks track overview. In Proceedings of TREC 2017 .Google Scholar
- Alexander Kotov, Paul N. Bennett, Ryen W. White, Susan T. Dumais, and Jaime Teevan. 2011. Modeling and analysis of cross-session search tasks. In Proceedings of SIGIR 2011, 5--14. Google ScholarDigital Library
- Matt J. Kusner, Yu Sun, Nicholas I. Kolkin, and Kilian Q. Weinberger. 2015. From word embeddings to document distances. In Proceedings of ICML 2015, 957--966. Google ScholarDigital Library
- Liangda Li, Hongbo Deng, Anlei Dong, Yi Chang, and Hongyuan Zha. 2014. Identifying and labeling search tasks via query-based Hawkes processes. In Proceedingsof KDD 2014, 731--740. Google ScholarDigital Library
- Zhen Liao, Yang Song, Yalou Huang, Li-wei He, and Qi He. 2014. Task trail: An effective segmentation of user search behavior. IEEE Trans. Knowl. Data Eng., Vol. 26, 12 (2014), 3090--3102.Google ScholarCross Ref
- Zheng Lu, Hongyuan Zha, Xiaokang Yang, Weiyao Lin, and Zhaohui Zheng. 2013. A new algorithm for inferring user search goals with feedback sessions. IEEE Trans. Knowl. Data Eng., Vol. 25, 3 (2013), 502--513. Google ScholarDigital Library
- Claudio Lucchese, Salvatore Orlando, Raffaele Perego, Fabrizio Silvestri, and Gabriele Tolomei. 2011. Identifying task-based sessions in search engine query logs. In Proceedings of WSDM 2011, 277--286. Google ScholarDigital Library
- Claudio Lucchese, Salvatore Orlando, Raffaele Perego, Fabrizio Silvestri, and Gabriele Tolomei. 2013. Discovering tasks from search engine query logs. ACM Trans. Inf. Syst., Vol. 31, 3 (2013), 14. Google ScholarDigital Library
- Rishabh Mehrotra, Prasanta Bhattacharya, and Emine Yilmaz. 2016. Deconstructing complex search tasks: A Bayesian nonparametric approach for extracting sub-tasks. In Proceedings of NAACL 2016, 599--605.Google ScholarCross Ref
- Rishabh Mehrotra and Emine Yilmaz. 2015. Terms, topics & tasks: Enhanced user modelling for better personalization. In Proceedings of ICTIR 2015, 131--140. Google ScholarDigital Library
- Rishabh Mehrotra and Emine Yilmaz. 2017a. Extracting hierarchies of search tasks & subtasks via a Bayesian nonparametric approach. In Proceedings of SIGIR 2017, 285--294. Google ScholarDigital Library
- Rishabh Mehrotra and Emine Yilmaz. 2017b. Task embeddings: Learning query embeddings using task context. In Proceedings of CIKM 2017, 2199--2202. Google ScholarDigital Library
- Donald Metzler, Susan T. Dumais, and Christopher Meek. 2007. Similarity measures for short segments of text. In Proceedings of ECIR 2007. 16--27. Google ScholarDigital Library
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv, Vol. abs/1301.3781 (2013).Google Scholar
- Greg Pass, Abdur Chowdhury, and Cayley Torgeson. 2006. A picture of search. In Proceedings of Infoscale 2006, 1. Google ScholarDigital Library
- Procheta Sen, Debasis Ganguly, and Gareth J. F. Jones. 2018. Tempo-lexical context driven word embedding for cross-session search task extraction. In Proceedings of NAACL 2018. 283--292.Google Scholar
- Amanda Spink, Minsoo Park, Bernard J. Jansen, and Jan O. Pedersen. 2006. Multitasking during web search sessions. Inf. Process. Manage., Vol. 42, 1 (2006), 264--275. Google ScholarDigital Library
- Manisha Verma and Emine Yilmaz. 2014. Entity oriented task extraction from query logs. Proceedings of CIKM 2014, 1975--1978. Google ScholarDigital Library
- Manisha Verma and Emine Yilmaz. 2016. Category oriented task extraction. In Proceedings of CHIIR 2016, 333--336. Google ScholarDigital Library
- Zi Yang and Eric Nyberg. 2015. Leveraging procedural knowledge for task-oriented search. In Proceedings of SIGIR 2015, 513--522. Google ScholarDigital Library
Index Terms
- Query-Task Mapping
Recommendations
User Behaviour and Task Characteristics: A Field Study of Daily Information Behaviour
CHIIR '17: Proceedings of the 2017 Conference on Conference Human Information Interaction and RetrievalPrevious studies investigating task based search often take the form of lab studies or large scale log analysis. In lab studies, users typically perform a designed task under a controlled environment, which may not reflect their natural behaviour. While ...
Query Reformulation for Task-Oriented Web Searches
WI-IAT '11: Proceedings of the 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Volume 03Web searches are driven by information needs and intend the accomplishment of specific tasks. Information needs are determined by the topical subject of queries, i.e. what we search, while tasks are determined by the user motives that induce the ...
Generating Query Suggestions to Support Task-Based Search
SIGIR '17: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information RetrievalWe address the problem of generating query suggestions to support users in completing their underlying tasks (which motivated them to search in the first place). Given an initial query, these query suggestions should provide a coverage of possible ...
Comments