Advertisement

A Normalized Framework Based on Multiple Relationships for Document Re-ranking

  • Wenyu Zhao
  • Dong ZhouEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10390)

Abstract

Document re-ranking has been widely adopted in Information Retrieval as a way of improving precision of top documents based on the first round retrieval results. There are methods that use semi-supervised learning based on graphs constructed based on similarities between documents. However, most of them only consider relationships between documents. In this paper, we propose an approach to take the relationships between documents, between words in documents, as well as between documents and words into consideration. We develop a novel generative model which integrates neural language model with latent semantic model, then we incorporate the relationships between documents and words into a normalized framework to re-rank documents based on the initial retrieval results. Experimental results show that the method show significant improvements in comparison with other baseline methods.

Keywords

Document re-ranking Word Embeddings Latent semantic model 

Notes

Acknowledgement

The work described in this paper was supported by National Natural Science Foundation of China under Project No. 61300129, Scientific Research Fund of Hunan Provincial Education Department of China under Project No. 16K030, Hunan Provincial Natural Science Foundation of China under Project No. 2017JJ2101, Hunan Provincial Innovation Foundation For Postgraduate under Project No. CX2016B575.

References

  1. 1.
    Zhang, Y., Jansen, B.J., Spink, A.: Time series analysis of a Web search engine transaction log. Inf. Process. Manage. 45(2), 230–245 (2009)CrossRefGoogle Scholar
  2. 2.
    Baliński, J., Daniłowicz, C.: Re-ranking method based on inter-document distances. Inf. Process. Manage. 41(4), 759–775 (2005)CrossRefzbMATHGoogle Scholar
  3. 3.
    Lee, K.S., Park, Y.C., Choi, K.S.: Re-ranking model based on document clusters. Inf. Process. Manage. 37(1), 1–14 (2001)CrossRefzbMATHGoogle Scholar
  4. 4.
    Zhou, D., Lawless, S., Wade, V.: Improving search via personalized query expansion using social media. Inf. Retrieval 15(3–4), 218–242 (2012)CrossRefGoogle Scholar
  5. 5.
    Zhou, D., Lawless, S., Wu, X., et al.: Enhanced personalized search using social data. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 700–710 (2016)Google Scholar
  6. 6.
    Diaz, F., Mitra, B., Craswell, N.: Query expansion with locally-trained word embeddings. In: Proceedings of the 2016 Conference on the Association for Computational Linguistics (2016)Google Scholar
  7. 7.
    Yang, L., Ji, D., Zhou, G., Nie, Y., Xiao, G.: Document re-ranking using cluster validation and label propagation. In: Proceedings of the 15th ACM International Conference on Information and Knowledge Management Arlington, Virginia, USA, pp. 690–697. ACM (2006)Google Scholar
  8. 8.
    Zhou, D., Wade, V.: Latent document re-ranking. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, vol. 3, Singapore, pp. 1571–1580. Association for Computational Linguistics (2009)Google Scholar
  9. 9.
    Vulić, I., Moens, M.-F.: Monolingual and cross-lingual information retrieval models based on (Bilingual) word embeddings. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, Santiago, Chile, pp. 363–372 (2015)Google Scholar
  10. 10.
    Ai, Q., Yang, L., Guo, J., et al.: Improving language estimation with the paragraph vector model for ad-hoc retrieval. In: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 869–872. ACM (2016)Google Scholar
  11. 11.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)zbMATHGoogle Scholar
  12. 12.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)Google Scholar
  13. 13.
    Plansangket, S., Gan, J.Q.: Re-ranking Google search returned web documents using document classification scores. Artif. Intell. Res. 6(1), 59 (2016)Google Scholar
  14. 14.
    Qu, Y., Xu, G., Wang, J.: Rerank method based on individual thesaurus. In: Proceedings of the Second NTCIR Workshop on Research in Chinese & Japanese Text Retrieval and Text Summarization Tokyo, Japan, National Institute of Informatics (2001)Google Scholar
  15. 15.
    Kamps, J.: Improving retrieval effectiveness by reranking documents based on controlled vocabulary. In: McDonald, S., Tait, J. (eds.) ECIR 2004. LNCS, vol. 2997, pp. 283–295. Springer, Heidelberg (2004). doi: 10.1007/978-3-540-24752-4_21 CrossRefGoogle Scholar
  16. 16.
    Luk, R.W.P., Wong, K.F.: Pseudo-relevance feedback and title re-ranking for Chinese information Retrieval. In: Proceedings of the Working Notes of the Fourth NTCIR Workshop Meeting Tokyo, Japan, National Institute of Informatics (2004)Google Scholar
  17. 17.
    Xu, J., Croft, W.B.: Improving the effectiveness of information retrieval with local context analysis. ACM Trans. Inform. Syst. (TOIS) 18(1), 79–112 (2000)CrossRefGoogle Scholar
  18. 18.
    Raviv, H., Kurland, O., Carmel, D.: Document retrieval using entity-based language models. In: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 65–74. ACM (2016)Google Scholar
  19. 19.
    Kurland, O., Lee, L.: PageRank without hyperlinks: structural re-ranking using links induced by language models. In: Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval Salvador, Brazil, pp. 306–313. ACM (2005)Google Scholar
  20. 20.
    Kurland, O., Lee, L.: Respect my authority!: HITS without hyperlinks, utilizing cluster-based language models. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval Seattle, Washington, USA, pp. 83–90. ACM (2006)Google Scholar
  21. 21.
    Kurland, O., Krikon, E.: The opposite of smoothing: a language model approach to ranking query specific document clusters. J. Artif. Intell. Res. (JAIR) 41, 367–395 (2011)zbMATHMathSciNetGoogle Scholar
  22. 22.
    Diaz, F.: Regularizing ad hoc retrieval scores. In: Proceedings of the 14th ACM International Conference on Information and Knowledge Management Bremen, Germany, pp. 672–679. ACM (2005)Google Scholar
  23. 23.
    Deng, H., Lyu, M.R., King, I.: Effective latent space graph-based re-ranking model with global consistency. In: Proceedings of the Second ACM International Conference on Web Search and Data Mining Barcelona, Spain, pp. 212–221. ACM (2009)Google Scholar
  24. 24.
    Zhang, B., Li, H., Liu, Y., Ji, L., Xi, W., Fan, W., Chen, Z., Ma, W.Y.: Improving web search results using affinity graph. In: Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Salvador, Brazil, pp. 504–511. ACM (2005)Google Scholar
  25. 25.
    Zhou, D., Lawless, S., Min, J., Wade, V.: Dual-space re-ranking model for document retrieval. In: Proceedings of the 23rd International Conference on Computational Linguistics: Posters, Beijing, China, pp. 1524–1532. Association for Computational Linguistics (2010)Google Scholar
  26. 26.
    Ermakova, L., Mothe, J.: Document re-ranking based on topic-comment structure. In: 2016 IEEE Tenth International Conference on Research Challenges in Information Science (RCIS), pp. 1–10. IEEE (2016)Google Scholar
  27. 27.
    Tu, X, Huang, J.X., Luo, J., et al.: Exploiting semantic coherence features for information retrieval. In: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 837–840. ACM (2016)Google Scholar
  28. 28.
    Heinrich, G.: Parameter estimation for text analysis. University of Leipzig, Technical report (2008)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringHunan University of Science and TechnologyXiangtanChina

Personalised recommendations