Multimedia Databases

1
Multimedia Databases

• Text II

2
Outline

• Spatial Databases
• Temporal Databases
• Spatio-temporal Databases
• Multimedia Databases
• Text databases
• Image and video databases
• Time Series databases
• Data Mining

3
Text - Detailed outline

• Text databases
• problem
• full text scanning
• inversion
• signature files
• clustering
• information filtering and LSI

4
Vector Space Model and Clustering

• keyword queries (vs Boolean)
• each document -gt vector (HOW?)
• each query -gt vector
• search for similar vectors

5
Vector Space Model and Clustering

• main idea

document
zoo
aaron
data
indexing
...data...
V ( vocabulary size)
6
Vector Space Model and Clustering

• Then, group nearby vectors together
• Q1 cluster search?
• Q2 cluster generation?
• Two significant contributions
• ranked output
• relevance feedback

7
Vector Space Model and Clustering

• cluster search visit the (k) closest
  superclusters continue recursively

MD TRs
CS TRs
8
Vector Space Model and Clustering

• ranked output easy!

MD TRs
CS TRs
9
Vector Space Model and Clustering

• relevance feedback (brilliant idea) Roccio73

MD TRs
CS TRs
10
Vector Space Model and Clustering

• relevance feedback (brilliant idea) Roccio73
• How?

MD TRs
CS TRs
11
Vector Space Model and Clustering

• How? A by adding the good vectors and
  subtracting the bad ones

MD TRs
CS TRs
12
Outline - detailed

• main idea
• cluster search
• cluster generation
• evaluation

13
Cluster generation

• Problem
• given N points in V dimensions,
• group them

14
Cluster generation

• Problem
• given N points in V dimensions,
• group them

15
Cluster generation

• We need
• Q1 document-to-document similarity
• Q2 document-to-cluster similarity

16
Cluster generation

• Q1 document-to-document similarity
• (recall bag of words representation)
• D1 data, retrieval, system
• D2 lung, pulmonary, system
• distance/similarity functions?

17
Cluster generation

• A1 of words in common
• A2 ........ normalized by the vocabulary sizes
• A3 .... etc
• About the same performance - prevailing one
• cosine similarity

18
Cluster generation

• cosine similarity
• sim(D1, D2) cos(?)
• sum(v1,i v2,i) / len(v1)/ len(v2)

D1
D2
?
19
Cluster generation

• cosine similarity - observations
• related to the Euclidean distance
• weights vi,j according to tf/idf

D1
D2
?
20
Cluster generation

• tf (term frequency)
• high, if the term appears very often in this
  document.
• idf (inverse document frequency)
• penalizes common words, that appear in almost
  every document

21
Cluster generation

• We need
• Q1 document-to-document similarity
• Q2 document-to-cluster similarity

?
22
Cluster generation

• A1 min distance (single-link)
• A2 max distance (all-link)
• A3 avg distance
• A4 distance to centroid

?
23
Cluster generation

• A1 min distance (single-link)
• leads to elongated clusters
• A2 max distance (all-link)
• many, small, tight clusters
• A3 avg distance
• in between the above
• A4 distance to centroid
• fast to compute

24
Cluster generation

• We have
• document-to-document similarity
• document-to-cluster similarity
• Q How to group documents into natural clusters

25
Cluster generation

• A many-many algorithms - in two groups
  VanRijsbergen
• theoretically sound (O(N2))
• independent of the insertion order
• iterative (O(N), O(N log(N))

26
Outline - detailed

• main idea
• cluster search
• cluster generation
• evaluation

27
Evaluation

• Q how to measure goodness of one distance
  function vs another?
• A ground truth (by humans) and
• precision and recall

28
Evaluation

• precision (retrieved and relevant) / retrieved
• 100 precision -gt no false alarms
• recall (retrieved and relevant)/ relevant
• 100 recall -gt no false dismissals

29
Text - Detailed outline

• text
• problem
• full text scanning
• inversion
• signature files
• clustering
• information filtering and LSI

30
LSI - Detailed outline

• LSI
• problem definition
• main idea
• experiments

31
Information Filtering LSI

• Foltz,92 Goal
• users specify interests ( keywords)
• system alerts them, on suitable news-documents
• Major contribution LSI Latent Semantic
  Indexing
• latent (hidden) concepts

32
Information Filtering LSI

• Main idea
• map each document into some concepts
• map each term into some concepts
• Concept a set of terms, with weights, e.g.
• data (0.8), system (0.5), retrieval (0.6)
  -gt DBMS_concept

33
Information Filtering LSI

• Pictorially term-document matrix (BEFORE)

34
Information Filtering LSI

• Pictorially concept-document matrix and...

35
Information Filtering LSI

• ... and concept-term matrix

36
Information Filtering LSI

• Q How to search, eg., for system?

37
Information Filtering LSI

• A find the corresponding concept(s) and the
  corresponding documents

38
Information Filtering LSI

• A find the corresponding concept(s) and the
  corresponding documents

39
Information Filtering LSI

• Thus it works like an (automatically constructed)
  thesaurus
• we may retrieve documents that DONT have the
  term system, but they contain almost everything
  else (data, retrieval)

40
LSI - Discussion - Conclusions

• Great idea,
• to derive concepts from documents
• to build a statistical thesaurus automatically
• to reduce dimensionality
• Often leads to better precision/recall
• but
• Needs training set of documents
• concept vectors are not sparse anymore

41
LSI - Discussion - Conclusions

• Observations
• Bellcore (-gt Telcordia) has a patent
• used for multi-lingual retrieval
• How exactly SVD works?

42
Indexing - Detailed outline

• primary key indexing
• secondary key / multi-key indexing
• spatial access methods
• fractals
• text
• SVD a powerful tool
• multimedia
• ...

43
References

• Foltz, P. W. and S. T. Dumais (Dec. 1992).
  "Personalized Information Delivery An Analysis
  of Information Filtering Methods." Comm. of ACM
  (CACM) 35(12) 51-60.
• Can, F. and E. A. Ozkarahan (Dec. 1990).
  "Concepts and Effectiveness of the
  Cover-Coefficient-Based Clustering Methodology
  for Text Databases." ACM TODS 15(4) 483-517.
• Rocchio, J. J. (1971). Relevance Feedback in
  Information Retrieval. The SMART Retrieval System
  - Experiments in Automatic Document Processing.
  G. Salton. Englewood Cliffs, New Jersey,
  Prentice-Hall Inc.

44
References - contd

• Salton, G. (1971). The SMART Retrieval System -
  Experiments in Automatic Document Processing.
  Englewood Cliffs, New Jersey, Prentice-Hall Inc.
• Salton, G. and M. J. McGill (1983). Introduction
  to Modern Information Retrieval, McGraw-Hill.
• Van-Rijsbergen, C. J. (1979). Information
  Retrieval. London, England, Butterworths.
• Zahn, C. T. (Jan. 1971). "Graph-Theoretical
  Methods for Detecting and Describing Gestalt
  Clusters." IEEE Trans. on Computers C-20(1)
  68-86.