Abstract
Predicting query performance, that is, the effectiveness of a search performed in response to a query, is a highly important and challenging problem. We present a novel approach to this task that is based on measuring the standard deviation of retrieval scores in the result list of the documents most highly ranked. We argue that for retrieval methods that are based on document-query surface-level similarities, the standard deviation can serve as a surrogate for estimating the presumed amount of query drift in the result list, that is, the presence (and dominance) of aspects or topics not related to the query in documents in the list. Empirical evaluation demonstrates the prediction effectiveness of our approach for several retrieval models. Specifically, the prediction quality often transcends that of current state-of-the-art prediction methods.
- Abdul-Jaleel, N., Allan, J., Croft, W. B., Diaz, F., Larkey, L., Li, X., Smucker, M. D., and Wade, C. 2004. UMASS at trec 2004 -- Novelty and hard. In Proceedings of the Text Retrieval Conference (TREC-13).Google Scholar
- Amati, G., Carpineto, C., and Romano, G. 2004. Query difficulty, robustness and selective application of query expansion. In Proceedings of the European Conference on IR Research (ECIR’04). 127--137.Google Scholar
- Arampatzis, A. and Robertson, S. 2011. Modeling score distributions in information retrieval. Inf. Retriev. 14, 1, 26--46. Google ScholarDigital Library
- Arampatzis, A., Kamps, J., and Robertson, S. 2009. Where to stop reading a ranked list? Threshold optimization using truncated score distributions. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 524--531. Google ScholarDigital Library
- Aslam, J. A. and Pavlu, V. 2007. Query hardness estimation using Jensen-Shannon divergence among multiple scoring functions. In Proceedings of the European Conference on IR Research (ECIR’07). 198--209. Google ScholarDigital Library
- Bendersky, M., Croft, W. B., and Diao, Y. 2011. Quality-Biased ranking of Web documents. In Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM’11). 95--104. Google ScholarDigital Library
- Bernstein, Y., Billerbeck, B., Garcia, S., Lester, N., Scholer, F., and Zobel, J. 2005. RMIT university at trec 2006: Terabyte and robust track. In Proceedings of the Text Retrieval Conference (TREC-14).Google Scholar
- Buckley, C. 2004. Why current IR engines fail. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. Poster. 584--585. Google ScholarDigital Library
- Buckley, C., Salton, G., Allan, J., and Singhal, A. 1994. Automatic query expansion using SMART: TREC3. In Proceedings of the Text Retrieval Conference (TREC-3). 69--80.Google Scholar
- Carmel, D. and Yom-Tov, E. 2010. Estimating the Query Difficulty for Information Retrieval. Synthesis Lectures on Information Concepts, Retrieval, and Services. Morgan & Claypool. Google ScholarDigital Library
- Carmel, D., Yom-Tov, E., Darlow, A., and Pelleg, D. 2006. What makes a query difficult? In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 390--397. Google ScholarDigital Library
- Clarke, C. L. A., Craswell, N., and Soboroff, I. 2009. Overview of the trec 2009 Web track. In Proceedings of the Text Retrieval Conference (TREC).Google Scholar
- Cormack, G. V., Smucker, M. D., and Clarke, C. L. A. 2010. Efficient and effective spam filtering and re-ranking for large Web datasets. CoRR abs/1004.5168.Google Scholar
- Croft, W. B. and Lafferty, J. 2003. Language Modeling for Information Retrieval. Information Retrieval Book Series, Number 13. Kluwer. Google ScholarDigital Library
- Cronen-Townsend, S., Zhou, Y., and Croft, W. B. 2002. Predicting query performance. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 299--306. Google ScholarDigital Library
- Cronen-Townsend, S., Zhou, Y., and Croft, W. B. 2004. A language modeling framework for selective query expansion. Tech. rep. IR-338, Center for Intelligent Information Retrieval, University of Massachusetts.Google Scholar
- Cronen-Townsend, S., Zhou, Y., and Croft, W. B. 2006. Precision prediction based on ranked list coherence. Inf. Retriev. 9, 6, 723--755. Google ScholarDigital Library
- Cummins, R., Jose, J. M., and O’Riordan, C. 2011a. Improved query performance prediction using standard deviation. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 1089--1090. Google ScholarDigital Library
- Cummins, R., Lalmas, M., O’Riordan, C., and Jose, J. M. 2011b. Navigating the user query space. In Proceedings of the International Symposium on String Processing and Information Retrieval (SPIRE’11). 380--385. Google ScholarDigital Library
- Dai, K., Kanoulas, E., Pavlu, V., and Aslam, J. A. 2011. Variational bayes for modeling score distributions. Inf. Retriev. 14, 1, 47--67. Google ScholarDigital Library
- Diaz, F. 2007. Performance prediction using spatial autocorrelation. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 583--590. Google ScholarDigital Library
- Fang, H. and Zhai, C. 2005. An exploration of axiomatic approaches to information retrieval. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 480--487. Google ScholarDigital Library
- Fang, H., Tao, T., and Zhai, C. 2004. A formal study of information retrieval heuristics. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 49--56. Google ScholarDigital Library
- Fuhr, N. 1992. Probabilistic models in information retrieval. Comput. J. 35, 3, 243--255. Google ScholarDigital Library
- Harman, D. 1992. Relevance feedback revisited. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 1--10. Google ScholarDigital Library
- Harman, D. and Buckley, C. 2004. The NRRC reliable information access (ria) workshop. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 528--529. Google ScholarDigital Library
- Hauff, C., Hiemstra, D., and de Jong, F. 2008a. A survey of preretrieval query performance predictors. In Proceedings of the International Conference on Information and Knowledge Management (CIKM’08). 1419--1420. Google ScholarDigital Library
- Hauff, C., Murdock, V., and Baeza-Yates, R. 2008b. Improved query difficulty prediction for the Web. In Proceedings of the International Conference on Information and Knowledge Management (CIKM’08). 439--448. Google ScholarDigital Library
- Hauff, C., Kelly, D., and Azzopardi, L. 2010. A comparison of user and system query performance predictions. In Proceedings of the International Conference on Information and Knowledge Management (CIKM’10). 979--988. Google ScholarDigital Library
- He, B. and Ounis, I. 2004. Inferring query performance using pre-retrieval predictors. In Proceedings of the International Symposium on String Processing and Information Retrieval (SPIRE’04). 43--54.Google Scholar
- Kanoulas, E., Dai, K., Pavlu, V., and Aslam, J. A. 2010. Score distribution models: Assumptions, intuition, and robustness to score manipulation. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 242--249. Google ScholarDigital Library
- Lafferty, J. D. and Zhai, C. 2001. Document language models, query models, and risk minimization for information retrieval. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 111--119. Google ScholarDigital Library
- Lavrenko, V. and Croft, W. B. 2001. Relevance-based language models. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 120--127. Google ScholarDigital Library
- Lin, J., Metzler, D., Elsayed, T., and Wang, L. 2010. Of ivory and smurfs: Loxodontan mapreduce experiments for Web search. In Proceedings of the Text Retrieval Conference (TREC).Google Scholar
- Liu, X. and Croft, W. B. 2008. Evaluating text representations for retrieval of the best group of documents. In Proceedings of the European Conference on IR Research (ECIR’08). 454--462. Google ScholarDigital Library
- Lv, Y. and Zhai, C. 2011. When documents are very long, bm25 fails! In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 1103--1104. Google ScholarDigital Library
- Manmatha, R., Rath, T. M., and Feng, F. 2001. Modeling score distributions for combining the outputs of search engines. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 267--275. Google ScholarDigital Library
- Metzler, D. and Croft, W. B. 2005. A Markov random field model for term dependencies. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 472--479. Google ScholarDigital Library
- Metzler, D. and Croft, W. B. 2007. Linear feature-based models for information retrieval. Inf. Retriev. 10, 3, 257--274. Google ScholarDigital Library
- Mitra, M., Singhal, A., and Buckley, C. 1998. Improving automatic query expansion. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 206--214. Google ScholarDigital Library
- Mothe, J. and Tanguy, L. 2005. Linguistic features to predict query difficulty. In ACM SIGIR’05 Workshop on Predicting Query Difficulty - Methods and Applications.Google Scholar
- Pérez-Iglesias, J. and Araujo, L. 2009. Ranking list dispersion as a query performance predictor. In Proceedings of the 2nd International Conference on Theory of Information Retrieval (ICTIR’09). 371--374. Google ScholarDigital Library
- Pérez-Iglesias, J. and Araujo, L. 2010. Standard deviation as a query hardness estimator. In Proceedings of the International Symposium on String Processing and Information Retrieval (SPIRE’10). 207--212. Google ScholarDigital Library
- Ponte, J. M. and Croft, W. B. 1998. A language modeling approach to information retrieval. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 275--281. Google ScholarDigital Library
- Raiber, F. and Kurland, O. 2010. On identifying representative relevant documents. In Proceedings of the International Conference on Information and Knowledge Management (CIKM’10). 99--108. Google ScholarDigital Library
- Robertson, S. 2007. On score distributions and relevance. In Proceedings of the European Conference on IR Research (ECIR’07). 40--51. Google ScholarDigital Library
- Robertson, S. E., Walker, S., Jones, S., Hancock-Beaulieu, M., and Gatford, M. 1994. Okapi at trec-3. In Proceedings of the Text Retrieval Conference (TREC).Google Scholar
- Rocchio, J. J. 1971. Relevance feedback in information retrieval. In The SMART Retrieval System: Experiments in Automatic Document Processing, G. Salton Ed., Prentice Hall, 313--323.Google Scholar
- Salton, J., Wong, A., and Yang, C. S. 1975. A vector space model for automatic indexing. Comm. ACM 18, 11, 613--620. Google ScholarDigital Library
- Scholer, F. and Garcia, S. 2009. A case for improved evaluation of query difficulty prediction. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 640--641. Google ScholarDigital Library
- Scholer, F., Williams, H. E., and Turpin, A. 2004. Query association surrogates for Web search. J. Am. Soc. Inf. Sci. Technol. 55, 7, 637--650. Google ScholarDigital Library
- Seo, J. and Croft, W. B. 2010. Geometric representations for multiple documents. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 251--258. Google ScholarDigital Library
- Shtok, A., Kurland, O., and Carmel, D. 2009. Predicting query performance by query-drift estimation. In Proceedings of the International Conference on Theory of Information Retrieval (ICTIR’09). 305--312. Google ScholarDigital Library
- Shtok, A., Kurland, O., and Carmel, D. 2010. Using statistical decision theory and relevance models for query performance prediction. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 259--266. Google ScholarDigital Library
- Song, F. and Croft, W. B. 1999. A general language model for information retrieval. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval (Poster abstract). 279--280. Google ScholarDigital Library
- Terra, E. L. and Warren, R. 2005. Poison pills: Harmful relevant documents in feedback. In Proceedings of the International Conference on Information and Knowledge Management (CIKM’05). 319--320. Google ScholarDigital Library
- Tomlinson, S. 2004. Robust, Web and terabyte retrieval with hummingbird search server at trec 2004. In Proceedings of the Text Retrieval Conference (TREC-13).Google Scholar
- Turtle, H. R. and Croft, W. B. 1990. Inference networks for document retrieval. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 1--24. Google ScholarDigital Library
- Vinay, V., Cox, I. J., Milic-Frayling, N., and Wood, K. R. 2006. On ranking the effectiveness of searches. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 398--404. Google ScholarDigital Library
- Voorhees, E. M. 2004. Overview of the trec 2004 robust retrieval track. In Proceedings of the Text Retrieval Conference (TREC-13).Google Scholar
- Yom-Tov, E., Fine, S., Carmel, D., and Darlow, A. 2005. Learning to estimate query difficulty: Including applications to missing content detection and distributed information retrieval. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 512--519. Google ScholarDigital Library
- Zhai, C. and Lafferty, J. D. 2001a. Model-Based feedback in the language modeling approach to information retrieval. In Proceedings of the International Conference on Information and Knowledge Management (CIKM’01). 403--410. Google ScholarDigital Library
- Zhai, C. and Lafferty, J. D. 2001b. A study of smoothing methods for language models applied to ad hoc information retrieval. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 334--342. Google ScholarDigital Library
- Zhao, Y., Scholer, F., and Tsegay, Y. 2008. Effective preretrieval query performance prediction using similarity and variability evidence. In Proceedings of the European Conference on IR Research (ECIR’08). 52--64. Google ScholarDigital Library
- Zhou, Y. 2007. Retrieval performance prediction and document quality. Ph.D. thesis, University of Massachusetts Amherst. Google ScholarDigital Library
- Zhou, Y. and Croft, W. B. 2006. Ranking robustness: A novel framework to predict query performance. In Proceedings of the International Conference on Information and Knowledge Management (CIKM’06). 567--574. Google ScholarDigital Library
- Zhou, Y. and Croft, W. B. 2007. Query performance prediction in Web search environments. In Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 543--550. Google ScholarDigital Library
Index Terms
- Predicting Query Performance by Query-Drift Estimation
Recommendations
Predicting Query Performance by Query-Drift Estimation
ICTIR '09: Proceedings of the 2nd International Conference on Theory of Information Retrieval: Advances in Information Retrieval TheoryPredicting <em>query performance</em> , that is, the effectiveness of a search performed in response to a query, is a highly important and challenging problem. Our novel approach to addressing this challenge is based on estimating the potential amount ...
Query-Performance Prediction Using Minimal Relevance Feedback
ICTIR '13: Proceedings of the 2013 Conference on the Theory of Information RetrievalThere has been much work on devising query-performance prediction approaches that estimate search effectiveness without relevance judgments (i.e., zero feedback). Specifically, post-retrieval predictors analyze the result list of top-retrieved ...
Query-performance prediction: setting the expectations straight
SIGIR '14: Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrievalThe query-performance prediction task has been described as estimating retrieval effectiveness in the absence of relevance judgments. The expectations throughout the years were that improved prediction techniques would translate to improved retrieval ...
Comments