1. Information Retrieval CSE 8337 Spring 2007 Query Operations Material for these slides obtained from: Modern Information Retrieval by Ricardo Baeza-Yates and Berthier Ribeiro-Neto http://www.sims.berkeley.edu/~hearst/irbook/ http://www.sims.berkeley.edu/~hearst/irbook/ Prof. Raymond J. Mooney in CS378 at University of Texas Introduction to Modern Information Retrieval by Gerald Salton and Michael J. McGill, 1983, McGraw-Hill. Automatic Text Processing, by Gerard Salton, Addison-Wesley,1989.

2. CSE 8337 Spring 2007 2 Operations TOC Introduction Relevance Feedback Query Expansion Term Reweighting Automatic Local Analysis Query Expansion using Clustering Automatic Global Analysis Query Expansion using Thesaurus Similarity Thesaurus Statistical Thesaurua Complete Link Algorithm

3. CSE 8337 Spring 2007 3 Query Operations Introduction IR queries as stated by the user may not be precise or effective. There are many techniques to improve a stated query and then process that query instead.

4. CSE 8337 Spring 2007 4 Relevance Feedback Use assessments by users as to the relevance of previously returned documents to create new (modify old) queries. Technique: 1. Increase weights of terms from relevant documents. 2. Decrease weight of terms from nonrelevant documents. Figure 10.4 in Automatic Text Processing Figure 6-10 in Introduction to Modern Information Retrieval

5. CSE 8337 Spring 2007 5 Relevance Feedback After initial retrieval results are presented, allow the user to provide feedback on the relevance of one or more of the retrieved documents. Use this feedback information to reformulate the query. Produce new results based on reformulated query. Allows more interactive, multi-pass process.

6. CSE 8337 Spring 2007 6 Relevance Feedback Architecture Rankings IR System Document corpus Ranked Documents 1. Doc1 2. Doc2 3. Doc3. 1. Doc1  2. Doc2  3. Doc3 . Feedback Query String Revise d Query ReRanked Documents 1. Doc2 2. Doc4 3. Doc5. Query Reformulation

7. CSE 8337 Spring 2007 7 Query Reformulation Revise query to account for feedback: Query Expansion: Add new terms to query from relevant documents. Term Reweighting: Increase weight of terms in relevant documents and decrease weight of terms in irrelevant documents. Several algorithms for query reformulation.

8. CSE 8337 Spring 2007 8 Query Reformulation for VSR Change query vector using vector algebra. Add the vectors for the relevant documents to the query vector. Subtract the vectors for the irrelevant docs from the query vector. This both adds both positive and negatively weighted terms to the query as well as reweighting the initial terms.

9. CSE 8337 Spring 2007 9 Optimal Query Assume that the relevant set of documents C r are known. Then the best query that ranks all and only the relevant queries at the top is: Where N is the total number of documents.

10. CSE 8337 Spring 2007 10 Standard Rochio Method Since all relevant documents unknown, just use the known relevant (D r ) and irrelevant (D n ) sets of documents and include the initial query q.  : Tunable weight for initial query.  : Tunable weight for relevant documents.  : Tunable weight for irrelevant documents.

11. CSE 8337 Spring 2007 11 Ide Regular Method Since more feedback should perhaps increase the degree of reformulation, do not normalize for amount of feedback:  : Tunable weight for initial query.  : Tunable weight for relevant documents.  : Tunable weight for irrelevant documents.

12. CSE 8337 Spring 2007 12 Ide “Dec Hi” Method Bias towards rejecting just the highest ranked of the irrelevant documents:  : Tunable weight for initial query.  : Tunable weight for relevant documents.  : Tunable weight for irrelevant document.

13. CSE 8337 Spring 2007 13 Comparison of Methods Overall, experimental results indicate no clear preference for any one of the specific methods. All methods generally improve retrieval performance (recall & precision) with feedback. Generally just let tunable constants equal 1.

14. CSE 8337 Spring 2007 14 Fair Evaluation of Relevance Feedback Remove from the corpus any documents for which feedback was provided. Measure recall/precision performance on the remaining residual collection. Compared to complete corpus, specific recall/precision numbers may decrease since relevant documents were removed. However, relative performance on the residual collection provides fair data on the effectiveness of relevance feedback. Fig 10.5 in Automatic Text Processing

15. CSE 8337 Spring 2007 15 Evaluating Relevance Feedback Test-and-control Collection Divide document collection in two parts Use test portion to perform relevance feedback and to modify query Perform test on control portion using both original and modified query Compare results

16. CSE 8337 Spring 2007 16 Why is Feedback Not Widely Used? Users sometimes reluctant to provide explicit feedback. Results in long queries that require more computation to retrieve, and search engines process lots of queries and allow little time for each one. Makes it harder to understand why a particular document was retrieved.

17. CSE 8337 Spring 2007 17 Pseudo Feedback Use relevance feedback methods without explicit user input. Just assume the top m retrieved documents are relevant, and use them to reformulate the query. Allows for query expansion that includes terms that are correlated with the query terms.

18. CSE 8337 Spring 2007 18 PseudoFeedback Results Found to improve performance on TREC competition ad-hoc retrieval task. Works even better if top documents must also satisfy additional boolean constraints in order to be used in feedback.

19. CSE 8337 Spring 2007 19 Term Reweighting for PM Use statistics found in retrieved documents D r – Set of relevant and retrieved D r,i – Set of relevant and retrieved that contain k i.

20. CSE 8337 Spring 2007 20 Term Reweighting No query expansion Document term weights not used Query term weights not used Therefore, not usually as effective as previous vector approach.

21. CSE 8337 Spring 2007 21 Local vs. Global Automatic Analysis Local – Documents retrieved are examined to automatically determine query expansion. No relevance feedback needed. Global – Thesaurus used to help select terms for expansion.

22. CSE 8337 Spring 2007 22 Automatic Local Analysis At query time, dynamically determine similar terms based on analysis of top-ranked retrieved documents. Base correlation analysis on only the “local” set of retrieved documents for a specific query. Avoids ambiguity by determining similar (correlated) terms only within relevant documents. “Apple computer”  “Apple computer Powerbook laptop”

23. CSE 8337 Spring 2007 23 Automatic Local Analysis Expand query with terms found in local clusters. D l – set of documents retireved for query q. V l – Set of words used in D l. S l – Set of distinct stems in V l. f si,j –Frequency of stem s i in document d j found in D l. Construct stem-stem association matrix.

24. CSE 8337 Spring 2007 24 Association Matrix w 1 w 2 w 3 …………………..w n w1w2w3..wnw1w2w3..wn c 11 c 12 c 13 …………………c 1n c 21 c 31. c n1 c ij : Correlation factor between stems s i and stem s j f ik : Frequency of term i in document k

25. CSE 8337 Spring 2007 25 Normalized Association Matrix Frequency based correlation factor favors more frequent terms. Normalize association scores: Normalized score is 1 if two stems have the same frequency in all documents.

26. CSE 8337 Spring 2007 26 Metric Correlation Matrix Association correlation does not account for the proximity of terms in documents, just co-occurrence frequencies within documents. Metric correlations account for term proximity. V i : Set of all occurrences of term i in any document. r(k u,k v ): Distance in words between word occurrences k u and k v (  if k u and k v are occurrences in different documents).

27. CSE 8337 Spring 2007 27 Normalized Metric Correlation Matrix Normalize scores to account for term frequencies:

28. CSE 8337 Spring 2007 28 Query Expansion with Correlation Matrix For each term i in query, expand query with the n terms, j, with the highest value of c ij (s ij ). This adds semantically related terms in the “neighborhood” of the query terms.

29. CSE 8337 Spring 2007 29 Problems with Local Analysis Term ambiguity may introduce irrelevant statistically correlated terms. “Apple computer”  “Apple red fruit computer” Since terms are highly correlated anyway, expansion may not retrieve many additional documents.

30. CSE 8337 Spring 2007 30 Automatic Global Analysis Determine term similarity through a pre-computed statistical analysis of the complete corpus. Compute association matrices which quantify term correlations in terms of how frequently they co-occur. Expand queries with statistically most similar terms.

31. CSE 8337 Spring 2007 31 Automatic Global Analysis There are two modern variants based on a thesaurus-like structure built using all documents in collection Query Expansion based on a Similarity Thesaurus Query Expansion based on a Statistical Thesaurus

32. CSE 8337 Spring 2007 32 Thesaurus A thesaurus provides information on synonyms and semantically related words and phrases. Example: physician syn: ||croaker, doc, doctor, MD, medical, mediciner, medico, ||sawbones rel: medic, general practitioner, surgeon,

33. CSE 8337 Spring 2007 33 Thesaurus-based Query Expansion For each term, t, in a query, expand the query with synonyms and related words of t from the thesaurus. May weight added terms less than original query terms. Generally increases recall. May significantly decrease precision, particularly with ambiguous terms. “interest rate”  “interest rate fascinate evaluate”

34. CSE 8337 Spring 2007 34 Similarity Thesaurus The similarity thesaurus is based on term to term relationships rather than on a matrix of co-occurrence. This relationship are not derived directly from co- occurrence of terms inside documents. They are obtained by considering that the terms are concepts in a concept space. In this concept space, each term is indexed by the documents in which it appears. Terms assume the original role of documents while documents are interpreted as indexing elements

35. CSE 8337 Spring 2007 35 Similarity Thesaurus The following definitions establish the proper framework t: number of terms in the collection N: number of documents in the collection f i,j : frequency of occurrence of the term ki in the document dj t j : vocabulary of document d j itf j : inverse term frequency for document d j

36. CSE 8337 Spring 2007 36 Similarity Thesaurus Inverse term frequency for document d j To k i is associated a vector

37. CSE 8337 Spring 2007 37 Similarity Thesaurus where w i,j is a weight associated to index- document pair[k i,d j ]. These weights are computed as follows

38. CSE 8337 Spring 2007 38 Similarity Thesaurus The relationship between two terms k u and k v is computed as a correlation factor c u,v given by The global similarity thesaurus is built through the computation of correlation factor c u,v for each pair of indexing terms [k u,k v ] in the collection

39. CSE 8337 Spring 2007 39 Similarity Thesaurus This computation is expensive Global similarity thesaurus has to be computed only once and can be updated incrementally

40. CSE 8337 Spring 2007 40 Query Expansion based on a Similarity Thesaurus Query expansion is done in three steps as follows:  Represent the query in the concept space used for representation of the index terms 2 Based on the global similarity thesaurus, compute a similarity sim(q,kv) between each term kv correlated to the query terms and the whole query q. 3 Expand the query with the top r ranked terms according to sim(q,kv)

41. CSE 8337 Spring 2007 41 Query Expansion - step one To the query q is associated a vector q in the term-concept space given by where w i,q is a weight associated to the index-query pair[k i,q]

42. CSE 8337 Spring 2007 42 Query Expansion - step two Compute a similarity sim(q,k v ) between each term k v and the user query q where c u,v is the correlation factor

43. CSE 8337 Spring 2007 43 Query Expansion - step three Add the top r ranked terms according to sim(q,k v ) to the original query q to form the expanded query q’ To each expansion term k v in the query q’ is assigned a weight w v,q’ given by The expanded query q’ is then used to retrieve new documents to the user

44. CSE 8337 Spring 2007 44 Query Expansion Sample Doc1 = D, D, A, B, C, A, B, C Doc2 = E, C, E, A, A, D Doc3 = D, C, B, B, D, A, B, C, A Doc4 = A c(A,A) = 10.991 c(A,C) = 10.781 c(A,D) = 10.781... c(D,E) = 10.398 c(B,E) = 10.396 c(E,E) = 10.224

45. CSE 8337 Spring 2007 45 Query Expansion Sample Query: q = A E E sim(q,A) = 24.298 sim(q,C) = 23.833 sim(q,D) = 23.833 sim(q,B) = 23.830 sim(q,E) = 23.435 New query: q’ = A C D E E w(A,q')= 6.88 w(C,q')= 6.75 w(D,q')= 6.75 w(E,q')= 6.64

46. CSE 8337 Spring 2007 46 WordNet A more detailed database of semantic relationships between English words. Developed by famous cognitive psychologist George Miller and a team at Princeton University. About 144,000 English words. Nouns, adjectives, verbs, and adverbs grouped into about 109,000 synonym sets called synsets.

47. CSE 8337 Spring 2007 47 WordNet Synset Relationships Antonym: front  back Attribute: benevolence  good (noun to adjective) Pertainym: alphabetical  alphabet (adjective to noun) Similar: unquestioning  absolute Cause: kill  die Entailment: breathe  inhale Holonym: chapter  text (part-of) Meronym: computer  cpu (whole-of) Hyponym: tree  plant (specialization) Hypernym: fruit  apple (generalization)

48. CSE 8337 Spring 2007 48 WordNet Query Expansion Add synonyms in the same synset. Add hyponyms to add specialized terms. Add hypernyms to generalize a query. Add other related terms to expand query.

49. CSE 8337 Spring 2007 49 Statistical Thesaurus Existing human-developed thesauri are not easily available in all languages. Human thesuari are limited in the type and range of synonymy and semantic relations they represent. Semantically related terms can be discovered from statistical analysis of corpora.

50. CSE 8337 Spring 2007 50 Query Expansion Based on a Statistical Thesaurus Global thesaurus is composed of classes which group correlated terms in the context of the whole collection Such correlated terms can then be used to expand the original user query This terms must be low frequency terms However, it is difficult to cluster low frequency terms To circumvent this problem, we cluster documents into classes instead and use the low frequency terms in these documents to define our thesaurus classes. This algorithm must produce small and tight clusters.

51. CSE 8337 Spring 2007 51 Query Expansion based on a Statistical Thesaurus Use the thesaurus class to query expansion. Compute an average term weight wt c for each thesaurus class C

52. CSE 8337 Spring 2007 52 Query Expansion based on a Statistical Thesaurus wt c can be used to compute a thesaurus class weight w c as

53. CSE 8337 Spring 2007 53 Query Expansion Sample TC = 0.90 NDC = 2.00 MIDF = 0.2 sim(1,3) = 0.99 sim(1,2) = 0.40 sim(2,3) = 0.29 sim(4,1) = 0.00 sim(4,2) = 0.00 sim(4,3) = 0.00 Doc1 = D, D, A, B, C, A, B, C Doc2 = E, C, E, A, A, D Doc3 = D, C, B, B, D, A, B, C, A Doc4 = A idf A = 0.0 idf B = 0.3 idf C = 0.12 idf D = 0.12 idf E = 0.60 q'=A B E E q= A E E

54. CSE 8337 Spring 2007 54 Query Expansion based on a Statistical Thesaurus Problems with this approach initialization of parameters TC,NDC and MIDF TC depends on the collection Inspection of the cluster hierarchy is almost always necessary for assisting with the setting of TC. A high value of TC might yield classes with too few terms

55. CSE 8337 Spring 2007 55 Complete link algorithm This is document clustering algorithm with produces small and tight clusters Place each document in a distinct cluster. Compute the similarity between all pairs of clusters. Determine the pair of clusters [C u,C v ] with the highest inter-cluster similarity. Merge the clusters C u and C v Verify a stop criterion. If this criterion is not met then go back to step 2. Return a hierarchy of clusters. Similarity between two clusters is defined as the minimum of similarities between all pair of inter- cluster documents

56. CSE 8337 Spring 2007 56 Selecting the terms that compose each class Given the document cluster hierarchy for the whole collection, the terms that compose each class of the global thesaurus are selected as follows Obtain from the user three parameters TC: Threshold class NDC: Number of documents in class MIDF: Minimum inverse document frequency

57. CSE 8337 Spring 2007 57 Selecting the terms that compose each class Use the parameter TC as threshold value for determining the document clusters that will be used to generate thesaurus classes This threshold has to be surpassed by sim(C u,C v ) if the documents in the clusters C u and C v are to be selected as sources of terms for a thesaurus class

58. CSE 8337 Spring 2007 58 Selecting the terms that compose each class Use the parameter NDC as a limit on the size of clusters (number of documents) to be considered. A low value of NDC might restrict the selection to the smaller cluster Cu+v

59. CSE 8337 Spring 2007 59 Selecting the terms that compose each class Consider the set of document in each document cluster pre-selected above. Only the lower frequency documents are used as sources of terms for the thesaurus classes The parameter MIDF defines the minimum value of inverse document frequency for any term which is selected to participate in a thesaurus class

60. CSE 8337 Spring 2007 60 Global vs. Local Analysis Global analysis requires intensive term correlation computation only once at system development time. Local analysis requires intensive term correlation computation for every query at run time (although number of terms and documents is less than in global analysis). But local analysis gives better results.

61. CSE 8337 Spring 2007 61 Query Expansion Conclusions Expansion of queries with related terms can improve performance, particularly recall. However, must select similar terms very carefully to avoid problems, such as loss of precision.

62. CSE 8337 Spring 2007 62 Conclusion Thesaurus is a efficient method to expand queries The computation is expensive but it is executed only once Query expansion based on similarity thesaurus may use high term frequency to expand the query Query expansion based on statistical thesaurus need well defined parameters