Recall: Query Reformulation Approaches

1
Recall Query Reformulation Approaches

• Relevance feedback based
• vector model (Rocchio )
• probabilistic model (Robertson Sparck Jones,
  Croft)
• Cluster based Query Expansion
• Local analysis derive information from retrieved
  document set
• Global analysis derive information from corpus

2
Local Analysis

• Known relevant documents contain terms which can
  be used to describe a larger cluster of relevant
  documents. MIR
• In relevance feedback, clusters are built from
  interaction with user about documents.
• Local analysis automatically exploits the
  documents retrieved by identifying terms related
  to those in the query.

3
Term Clusters

• Association Clusters model co-occurrence of
  stems in retrieved documents, expand using
  co-occurring terms
• unnormalized groups by large frequencies
• normalized groups by rarity
• Metric Clusters factor in intra-document
  distance
• Problem Expensive to compute on the fly

4
Global Analysis

• All documents are analyzed for term
  relationships.
• Two Approaches
• Similarity thesaurus relates whole query to new
  terms. Focus is on concept underlying terms each
  term is indexed by the documents in which it
  appears.
• Statistical thesaurus cluster documents into
  class hierarchy

5
Similarity Thesaurus Basis

• where inverse term frequency (itf) for doc dj is

N is the number of documents, t is number of
distinct terms in collection and tj is number of
distinct terms in document j
6
Similarity Thesaurus Creation

• Thesaurus is a matrix of correlation factors
  between indexing terms

7
Relationship between terms and Query
from Qiu Frei, Concept Based Query Expansion,
SIGIR-93
8
Query Expansion w/Similarity Thesaurus

• Represent the query in the concept space of the
  index terms (weight vector)
• Based on the global similarity thesaurus, compute
  a similarity sim(q,kv)
• Expand the query with the top r ranked terms and
  weight with

9
Global 2 Statistical Thesaurus

• Thesaurus construction relies on high
  discrimination/low frequency terms.
• Hard to cluster
• So, build classes based on clustering similar
  docs instead.
• Similarity is minimum of cosine vector model
  similarity between any two docs (one from each
  cluster).

10
Complete Link Algorithm Crouch Yang

• Place each document in a distinct cluster.
• Compute the similarity between all pairs of
  clusters.
• Determine the pair of clusters Cu,Cv with the
  highest inter-cluster similarity.
• Merge the clusters Cu and Cv
• Verify a stop criterion. If this criterion is not
  met then go back to step 2.
• Return a hierarchy of clusters.

11
Hierarchy Example

• Doc1D,D,A,B,C,A,B,C
• Doc2E,C,E,A,A,D
• Doc3D,C,B,B,D,A,B,C,A
• Doc4A
• from MIR notes

12
Query Expansion w/Statistical Thesaurus

• Select the terms for each class
• Threshold on similarity determines which clusters
• NDC determines max number of docs in cluster
• MIDF determines minimum IDF for any term (i.e.,
  how rare)
• Compute thesaurus class weight for terms

13
Global Analysis Summary

• Thesaurus approach has been effective for
  improving queries
• However
• requires expensive processing (static corpus
  required)
• statistical generation exploits small frequencies
  better but is sensitive to parameter settings.

14
Relevance Feedback/Query Reformulation Summary

• Relevance feedback and query expansion approaches
  have been shown to be effective at improving
  relevance, sometimes at expense of precision.
• Users resist relevance feedback, takes time and
  understanding.
• Query reformulation can be costly (expensive
  computation) for search engines/IR systems.

15
Search Engine Use of Query Feedback

• Relevance feedback
• explicit tried, but mostly abandoned.
• indirect Teoma (ranks documents higher that
  users look at more often)
• Similar/Related Pages or searches
• suggest expanded queries or ask to search for
  related pages (Altavista and MSN Search used to
  do this)
• Google- Find Similar
• Teoma
• Web log data mining

16
Behavior-Based Ranking

• AskJeeves used user behavior to change results
  ranking
• For each query Q, record which URLs are followed
• Use click through counts to order URLs for
  subsequent submissions of Q
• Pseudo-relevance feedback

17
Teoma Indirect Relevance

• Combines indirect relevancy judgments with their
  own link analysis
• Subject-Specific Popularity ranks a site based
  on the number of same-subject specific pages that
  reference it. Teoma.com page
• Clustering Usage
• Refine Models communities to suggest search
  classification
• Resources Suggests authoritative sites within
  designated community

18
Web Log Mining

• SOP for large search engines to monitor what
  people are querying
• Goals
• learn associations between common terms based on
  large number of queries
• Identify trends in user behavior that should be
  addressed by system