Boosting novelty for biomedical information retrieval through probabilistic latent semantic analysis

ABSTRACT

In information retrieval, we are interested in the information that is not only relevant but also novel. In this paper, we study how to boost novelty for biomedical information retrieval through probabilistic latent semantic analysis. We conduct the study based on TREC Genomics Track data. In TREC Genomics Track, each topic is considered to have an arbitrary number of aspects, and the novelty of a piece of information retrieved, called a passage, is assessed based on the amount of new aspects it contains. In particular, the aspect performance of a ranked list is rewarded by the number of new aspects reached at each rank and penalized by the amount of irrelevant passages that are rated higher than the novel ones. Therefore, to improve aspect performance, we should reach as many aspects as possible and as early as possible. In this paper, we make a preliminary study on how probabilistic latent semantic analysis can help capture different aspects of a ranked list, and improve its performance by re-ranking. Experiments indicate that the proposed approach can greatly improve the aspect-level performance over baseline algorithm Okapi BM25.

References

1. A. Asuncion and et al. On smoothing and inference for topic models. In UAI'09, pages 27--34, 2009.
2. D. M. Blei and et al. Latent dirichlet allocation. JMLR, 3(4-5):993--1022, 2003.
3. J. Carbonell and J. Goldstein. The use of MMR, diversity-based reranking for reordering documents and producing summaries. In SIGIR'98, pages 335--336.
4. C. Clarke and et al. Novelty and diversity in information retrieval evaluation. In SIGIR'08, pages 659--666.
5. S. Deerwester and et al. Indexing by latent semantic analysis. JASIST, 41, 1990.
6. D. Demner-Fushman and et al. Combining resources to find answers to biomedical questions. In TREC-2007, pages 205--214.
7. A. B. Goldberg and et al. Ranking biomedical passages for relevance and diversity: University of Wisconsin, Madison at TREC genomics 2006. In TREC-2006, pages 129--136.
8. W. Hersh, A. Cohen, and P. Roberts. TREC 2007 genomics track overview. In TREC-2007, pages 98--115.
9. T. Hofmann. Probabilistic latent semantic analysis. In UAI'99, pages 289--296.
10. Q. Hu and X. Huang. A reranking model for genomics aspect search. In SIGIR'08, pages 783--784.
11. X. Huang and et al. A platform for okapi-based contextual information retrieval. In SIGIR'06, pages 728--728, 2006.
12. X. Huang and Q. Hu. A bayesian learning approach to promoting diversity in ranking for biomedical informaiton retrieval. In SIGIR'09, pages 307--314.
13. X. Yin and et al. Survival modeling approach to biomedical search result diversification using wikipedia. TKDE, 25(6):1201--1212, 2013.
14. C. Zhai, W. W. Cohen, and J. Lafferty. Beyond independent relevance: methods and evaluation metrics for subtopic retrieval. In SIGIR'03, pages 10--17.
15. B. Zhang and et al. Improving web search results using affinity graph. In SIGIR'05, pages 504--511.
16. Y. Zhang, J. Callan, and T. Minka. Novelty and redundancy detection in adaptive filtering. In SIGIR'02, pages 81--88.
17. W. Zhou and C. Yu. TREC genomics track at UIC. In TREC-2007, pages 221--226.
18. X. Zhu and et al. Improving diversity in ranking using absorbing random walks. In NAACL-HLT 2007, pages 97--104.

Index Terms

• Information systems

  • Information retrieval