1. Dependency Network Based Real-time Query Expansion Jiaqi Zou, Xiaojie Wang Center for Intelligence Science and Technology, BUPT

2. Outline Introduction –What is RTQE?What is RTQE? –Benefits of RTQEBenefits of RTQE –Related ResearchRelated Research –Improvements in our workImprovements in our work Method –Query IntentionQuery Intention –Dependency Relation NetworkDependency Relation Network –RTQE MethodRTQE Method

3. Outline Experiments –Test of operation numbersTest of operation numbers –Test of expansion success percentageTest of expansion success percentage –Test of retrieval performanceTest of retrieval performance –Comparison with BingComparison with Bing Conclusion

4. Introduction- What is RTQE? RTQE is a kind of query expansion. RTQE methods expand queries at the same time when users type queries into the search box.

5. Introduction- Benefits of RTQE RTQE reduces user’s keystrokes and time to perform a query, especially useful for mobile device users. RTQE improves the query quality.

6. Related Research Most widely used method: string matching method using query log. Little work on RTQE takes query intention into account. –Strohmaier et al. suggested that explicit queries containing at least one verb word might reflect possible user intentions.

7. Improvements in our work Represent query intention better. Construct a RTQE method which expands components of possible user query intentions. This RTQE method improves the retrieval performance.

8. Query Intention Task-oriented classification of query intention: –Navigational –Informational –Transactional Duan et al. suggested dependency related verb-noun pairs are good representation of informational and transactional query intentions.

9. Query Intention Verb-noun pair is not sufficient to represent query intention, other parts like attributes of noun are also very important. New representation: Verb-Attributes-Noun Example: buy new car tire, cook Chinese food

10. Dependency Relation Network To do query intention related RTQE, we built a dependency relation network which is a collection of numbers of query intentions. Steps: –Do dependency parsing on large corpus. –Extract all the verb-attributes-noun structures. –Combine these structures to be the Network.

11. Dependency Relation Network Example : How to change a car tire Extracted : change car tire

12. RTQE method

13. RTQE Example

14. Experiments Corpus: www.ehow.com –915,000 articles –20 categories(Health, Cars, Food&Drink, etc)

15. Test of operation numbers Keystrokes and mouse clicks needed to generate a query is recorded. Each keystroke or mouse click is recorded as an operation.

16. Test of operation numbers Average saved operations is 63.75% after RTQE Average number of operations Without RTQEWith RTQE 15.05.437

17. Test of expansion success percentage For a given query intention, if the user can find a query exactly related to this intention from the expanded list, we call it a successful expansion.

18. Test of expansion success percentage Times Query expansion success Query expansion fail 16832 Expansion success percentage is 84%.

19. Test of retrieval performance We compare the retrieval performance of the three: –original query user typed in –the query after verb-noun expansion –the query after verb-attributes-noun expansion. We use precision and nDCG score for evaluation.

20. Test of retrieval performance Query TypePrecisionnDCG score Original query word0.73%13.11% Query after verb-noun expansion 9.47%37.37% Query after verb- attributes-noun expansion 79.2%88.95%

21. Comparison with Bing The RTQE result of Bing differs a lot if the word order of a query changes.

22. Comparison with Bing Categories the RTQE result of Bing into 3 groups: –NOT: cannot get correct recommendations –NORMAL: get correct recommendations only in normal word order –ALL: can get correct recommendations both in normal order and other word orders

23. Comparison with Bing GroupNOTNORMALALL Percentage49%33%18%

24. Conclusion Presented a novel RTQE method using a dependency relation network. This RTQE method is proved to be effective in representing user query intention and hence improve retrieval performance.

25. Thank you!