Massive Query Expansion by Exploiting Graph Knowledge Bases for Image Retrieval

ABSTRACT

Annotation-based techniques for image retrieval suffer from sparse and short image textual descriptions. Moreover, users are often not able to describe their needs with the most appropriate keywords. This situation is a breeding ground for a vocabulary mismatch problem resulting in poor results in terms of retrieval precision. In this paper, we propose a query expansion technique for queries expressed as keywords and short natural language descriptions. We present a new massive query expansion strategy that enriches queries using a graph knowledge base by identifying the query concepts, and adding relevant synonyms and semantically related terms. We propose a topological graph enrichment technique that analyzes the network of relations among the concepts, and suggests semantically related terms by path and community detection analysis of the knowledge graph. We perform our expansions by using two versions of Wikipedia as knowledge base achieving improvements of the system's precision up to more than 27%.

References

1. J. Arguello, J. Elsas, J. Callan, and J. Carbonell. Document representation and query expansion models for blog recommendation. In ICWSM, 2008.
2. C. Carpineto and G. Romano. A survey of automatic query expansion in information retrieval. CSUR, 44(1):1, 2012.
3. Y. Chang, I. Ounis, and M. Kim. Query reformulation using automatically generated query concepts from a document space. IPM, 42(2):453--468, 2006.
4. V. Dang and W. Croft. Query reformulation using anchor text. In WSDM, pages 41--50, 2010.
5. O. Egozi, S. Markovitch, and E. Gabrilovich. Concept-based information retrieval using explicit semantic analysis. TOIS, 29(2):8, 2011.
6. N. Eiron and K. McCurley. Analysis of anchor text for web search. In SIGIR, pages 459--460, 2003.
7. J. Hu, G. Wang, F. Lochovsky, J. Sun, and Z. Chen. Understanding user's query intent with wikipedia. In WWW, pages 471--480, 2009.
8. B. Jansen and A. Spink. How are we searching the world wide web? A comparison of nine search engine transaction logs. IPM, 42(1):248--263, 2006.
9. N. Martínez-Bazan, M. Aguila-Lorente, and V. Muntés-Mulero. Efficient graph management based on bitmap indices. In IDEAS, pages 110--119, 2012.
10. D. Metzler and W. Croft. Combining the language model and inference network approaches to retrieval. IPM, 40(5):735--750, 2004.
11. D. Milne, I. Witten, and D. Nichols. A knowledge-based search engine powered by wikipedia. In CIKM, pages 445--454, 2007.
12. C. Paice. An evaluation method for stemming algorithms. In SIGIR, pages 42--50, 1994.
13. A. Prat-Pérez, D. Dominguez-Sal, J. Brunat, and J. Larriba-Pey. Shaping communities out of triangles. In CIKM, pages 1677--1681, 2012.
14. Y. Song, D. Zhou, and L. He. Query suggestion by constructing term-transition graphs. In WSDM, pages 353--362, 2012.
15. T. Strohman, D. Metzler, H. Turtle, and B. Croft. Indri: A language model-based search engine for complex queries. In ICIA, volume 2, pages 2--6. Citeseer, 2005.
16. F. Suchanek, G. Kasneci, and G. Weikum. Yago: a core of semantic knowledge. In WWW, pages 697--706, 2007.
17. B. Truong, A. Sun, and S. Bhowmick. Content is still king: the effect of neighbor voting schemes on tag relevance for social image retrieval. In ICMR, page 9, 2012.
18. H. Turtle, Y. Hegde, and S. Rowe. Yet another comparison of lucene and indri performance. In SIGIR 2012 Workshop on Open Source Information Retrieval, pages 64--67, 2012.
19. L. Wu, R. Jin, and A. K. Jain. Tag completion for image retrieval. TPAMI, 35(3):716--727, 2013.
20. A. Znaidia, H. Borgne, and C. Hudelot. Tag completion based on belief theory and neighbor voting. In ICMR, pages 49--56, 2013.

Index Terms

• Information systems

  • Information retrieval