Summary of SIGIR 2011 Papers
- 1. Summary of Papers of SIGIR 2011 Workshop on Query Representation and Understanding Chetana Gavankar
- 2. Ricardo Campos, Alipio Jorge, Gael Dias: "Using Web Snippets and Query-logs to Measure Implicit Temporal Intents in Queries"
- 3. Temporal queries 1. Atemporal : Queries not sensitive to time like plan my trip 2. Temporal unambiguous : Queries in concrete time period. Ex : Haiti earthquake in 2010 3. Temporal ambiguous : queries with multiple instances over time. Ex : Cricket worldcup which occurs every four years.
- 4. Web snippets and Query Logs Content-Related Resources , based on a web content approach Simply requires the set of web search results. Query-Log Resources , based on similar year-qualified queries Imply that some versions of the query have already been issued.
- 5. 1. Web snippets ( temporal evidence within web pages): TA(q)= ∑ f ε I w f f(q) I = {Tsnippet(.),TTitle(.),TUrl(.)} Value each feature differently using w f 18.14 for TTitles, 50.91 for TSnippets and 30.95 for Turl(.) If TA(q) value < 10% then Atemporal. Dates appearing in query & docs may not match. # Snippets Retrieved with Dates Identifying implicit temporal queries TSnippets = # Snippets Retrieved
- 6. Identifying implicit temporal queries 2.Web Query Logs : Temporal activity can be recorded from date & time of request and from user activity. No. of times query is pre, post qualified by year is WA(q,y)=#(y,q) + #(q,y) α(q) = ∑ y WA (q,y) / ∑ x #(x,q) + ∑ x #(q,x) If query qualified with single year then α(q) =1
- 7. Results Temporal information is more frequent in web snippets than in any of the query logs of Google and Yahoo!; Most of the queries have a TSnippet(.) value around 20%, TLogYahoo(.) and TLogGoogle(.) are mostly near to 0%.
- 8. Conclusion Future dates common in snippets than query log
- 9. Query having dates does not necessarily mean that it has temporal intent (from web query logs of Google and yahoo) Ex: October Sky movie
- 10. Web snippets statistically more relevant in terms of temporal intent than query logs
- 11. Rishiraj Saha Roy, Niloy Ganguly, Monojit Choudhury, Naveen Singh: "Complex Network Analysis Reveals Kernel-Periphery Structure in Web Search Queries"
- 12. Search Queries Search Query language: bag of segments Word occurrence n/w: Edge exists if P ij > P i P j Eight complex network models for query logs Query Unrestricted wordnet(local) and (global)
- 13. Query Restricted wordnet(local) and (global)
- 14. Query Unrestricted SegmentNet(local) and (global)
- 15. Query Restricted SegmentNet(local) and (global)
- 16. Kernel and Peripheral lexicons Two regimes in DD of word occurrence N/W: 1.K ernel lexicons (K-Lex or modifiers): Units popular in query (high degrees)
- 17. Generic and domain independent
- 18. Ex: how to, wikipedia 2.Peripheral lexicon (P-Lex or HEADs): Rare ones with degree much less than those in kernel Ex: Decision Tree algorithm
- 19. Degree Disribution |N| = Nodes, |E| = edges C= average clustering coefficient d=mean shortest path between edges C rand and d rand are corr. Values in random graph C rand ~ k'/ |N| , d rand ~ ln(|N|)/ ln(|k'|) k' = average degree of graph Degree distribution= p(k) = nodes with degree k/ total nodes
- 20. Two regime power law
- 21. Conclusion Like NL, Queries reflect kernal-periphery distinction
- 22. Unlike NL, Query N/W lack small word property for quickly retrieving words from mind
- 23. More difficult to understand context of segment in query.
- 24. Peripheral N/W consist of large number of small disconnected components
- 25. Capability of peripheral units to exist by themselves makes POS identification hard in Queries.
- 26. Socio-cultural factors govern the kernel-periphery distinction in queries
- 27. Lidong Bing, Wai Lam: "Investigation of Web Query Refinement via Topic Analysis and Learning with Personalization"
- 28. Web Query Refinement Query Refinement Substitution
- 29. Expansion
- 30. Deletion
- 31. Stemming
- 34. ...................... Generate some candidate queries first, and score the quality of these candidates.
- 35. Latent Topic Analysis in Query Log Query log record (user_id, query, clicked_url, time) Pseudo-document generation: Queries related to the same host are aggregated. General sites like “en.wikipedia.org” are not suitable for latent topic analysis & are eliminated Latent Dirichlet Allocation Algorithm) LDA to conduct the latent semantic topic analysis on the collection of host-based pseudo-documents. Z = set of latent topic s z i Each z i is associated with multinomial distribution of terms P ( tk | z i )= prob of term tk given topic z i
- 36. Personalization π u ={ π u 1 , π u 2 , … , π u |z| } = profile of the user u , π u i = P ( z i | u ) = probability that the user u prefers the topic z i Generate user-based pseudo-document U for user u . { P ( z 1 | U ), P ( z 2 | U ), … , P ( z | Z | | U )} = profile of u . candidate query q : t 1 , … t n Topic of term t r = z r
- 37. Topic based scoring with personalization Candidate query score: model parameter P ( zj | zi ) captures the relationship of two topics With personal profile P ( z 1 | u ) = probability that user u prefers the topic z 1
- 38. Conclusion Framework that considers personalization achieves the best performance. With user profiles, the topic-based scoring part is more reliable