ABSTRACT
We consider an interactive information retrieval task in which the user is interested in finding several to many relevant documents with minimal effort. Given an initial document ranking, user interaction with the system produces relevance feedback (RF) which the system then uses to revise the ranking. This interactive process repeats until the user terminates the search. To maximize accuracy relative to user effort, we propose an active learning strategy. At each iteration, the document whose relevance is maximally uncertain to the system is slotted high into the ranking in order to obtain user feedback for it. Simulated feedback on the Robust04 TREC collection shows our active learning approach dominates several standard RF baselines relative to the amount of feedback provided by the user. Evaluation on Robust04 under noisy feedback and on LETOR collections further demonstrate the effectiveness of active learning, as well as value of negative feedback in this task scenario.
- B. Bai, J. Weston, D. Grangier, R. Collobert, K. Sadamasa, Y. Qi, O. Chapelle, and K. Weinberger. Learning to rank with (a lot of) word features. Information Retrieval, 13(3):291--314, 2010. Google ScholarDigital Library
- M. Belkin and P. Niyogi. Laplacian eigenmaps and spectral techniques for embedding and clustering. NIPS, 1:585--592, 2002.Google Scholar
- C. Brandt, T. Joachims, Y. Yue, and J. Bank. Dynamic ranked retrieval. In Proc. WSDM, pages 247--256. ACM, 2011. Google ScholarDigital Library
- C. Buckley and S. Robertson. Relevance feedback track overview. In 17th TREC Notebook, 2008.Google Scholar
- W. Cooper. Expected search length: A single measure of retrieval effectiveness based on the weak ordering action of retrieval systems. American Documentation, 19(1):30--41, 1968.Google ScholarCross Ref
- G. Cormack, C. Clarke, and S. Buttcher. Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In SIGIR, pages 758--759, 2009. Google ScholarDigital Library
- N. Craswell and D. Hawking. Overview of the TREC-2004 Web track. In Proc. TREC, 2005.Google Scholar
- S. Deerwester, S. Dumais, G. Furnas, T. Landauer, and R. Harshman. Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41(6):391--407, 1990.Google ScholarCross Ref
- F. Diaz and D. Metzler. Improving the estimation of relevance models using large external corpora. In Proc. SIGIR, pages 154--161. ACM, 2006. Google ScholarDigital Library
- X. He, D. Cai, and P. Niyogi. Laplacian score for feature selection. NIPS, 18:507, 2006.Google ScholarDigital Library
- X. He and P. Niyogi. Locality preserving projections. NIPS, 16:153, 2004.Google Scholar
- T. Hofmann. Probabilistic latent semantic indexing. In Proc. SIGIR, pages 50--57. ACM, 1999. Google ScholarDigital Library
- A. Kapoor, E. Horvitz, and S. Basu. Selective supervision: guiding supervised learning with decision-theoretic active learning. In IJCAI, pages 877--882, 2007. Google ScholarDigital Library
- P. Over. The TREC interactive track: an annotated bibliography. Information Processing & Management, 37(3):369--381, 2001. Google ScholarDigital Library
- T. Qin, T. Liu, J. Xu, and H. Li. LETOR: A benchmark collection for research on learning to rank for information retrieval. Information Retrieval, pages 1--29, 2010. Google ScholarDigital Library
- F. Radlinski and S. Dumais. Improving personalized web search using result diversification. In Proc. SIGIR, pages 691--692. ACM, 2006. Google ScholarDigital Library
- F. Radlinski and T. Joachims. Active exploration for learning rankings from clickthrough data. In Proc. SIGKDD, pages 570--579. ACM, 2007. Google ScholarDigital Library
- D. Rafiei, K. Bharat, and A. Shukla. Diversifying web search results. In WWW, pages 781--790. ACM, 2010. Google ScholarDigital Library
- S. Robertson. The probability ranking principle in IR. Journal of Documentation, 33(4):294--304, 1977.Google ScholarCross Ref
- G. Salton and C. Buckley. Improving retrieval performance by relevance feedback. Journal of the American Society for Information Science, 41(4):288--297, 1990.Google ScholarCross Ref
- R. Schapire. A brief introduction to boosting. In Proc. IJCAI, volume 16, pages 1401--1406, 1999. Google ScholarDigital Library
- M. D. Smucker, J. Allan, and B. Carterette. A comparison of statistical significance tests for information retrieval evaluation. In Proc. of CIKM, pages 623--632, 2007. Google ScholarDigital Library
- T. Strohman, D. Metzler, H. Turtle, and W. B. Croft. Indri: A language model-based search engine for complex queries. In Proceedings of the International Conference on Intelligence Analysis, 2004.Google Scholar
- S. Tong and D. Koller. Support vector machine active learning with applications to text classification. The Journal of Machine Learning Research, 2:45--66, 2002. Google ScholarDigital Library
- J. Wang and J. Zhu. Portfolio theory of information retrieval. In Proc. SIGIR, pages 115--122. ACM, 2009. Google ScholarDigital Library
- X. Wang, H. Fang, and C. Zhai. A study of methods for negative relevance feedback. In Proc. SIGIR, pages 219--226. ACM, 2008. Google ScholarDigital Library
- X. Wei and W. Croft. LDA-based document models for ad-hoc retrieval. In SIGIR, pages 178--185, 2006. Google ScholarDigital Library
- C. Zhai and J. Lafferty. Model-based feedback in the language modeling approach to information retrieval. In Proc. CIKM, pages 403--410. ACM, 2001. Google ScholarDigital Library
Index Terms
- Active learning to maximize accuracy vs. effort in interactive information retrieval
Recommendations
Optimization on active learning strategy for object category retrieval
ICIP'09: Proceedings of the 16th IEEE international conference on Image processingActive learning is a machine learning technique which has attracted a lot of research interest in the content-based image retrieval (CBIR) in recent years. To be effective, an active learning system must be fast and efficient using as few (relevance) ...
Intention-focused active reranking for image object retrieval
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementWe consider the problem of ranking refinement for image object retrieval, whose goal is to improve an existing ranking function by a small number of labeled instances. To retrieve the relevant image object, one state-of-the-art approach is to use the ...
SVM-based Interactive Document Retrieval with Active Learning
AbstractThis paper describes an application of SVM (Support Vector Machines) to interactive document retrieval using active learning. Some works have been done to apply classification learning like SVM to relevance feedback and have obtained successful ...
Comments