Your SlideShare is downloading. ×
SQE - Semantic Query Expansion
SQE - Semantic Query Expansion
SQE - Semantic Query Expansion
SQE - Semantic Query Expansion
SQE - Semantic Query Expansion
SQE - Semantic Query Expansion
SQE - Semantic Query Expansion
SQE - Semantic Query Expansion
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

SQE - Semantic Query Expansion

4,263

Published on

Overview of semantic query expansion algorithm allowing to do searches based on users' profiles

Overview of semantic query expansion algorithm allowing to do searches based on users' profiles

Published in: Technology, Education
0 Comments
2 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total Views
4,263
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
84
Comments
0
Likes
2
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide
  • - What it will be about etc.
  • Transcript

    • 1. SQE – Semantic Query Expansion Digital Enterprise Research Institute National University of Ireland, Galway [email_address] jakub.demczuk @deri.org [email_address] [email_address]
    • 2. Outline
      • Motivations
      • Algorithm overview
      • Ideas
    • 3. SQE motivations:
      • Why?
        • Simple search returns too many results
        • Keyword search must be precise
        • Ambiguity of words
    • 4. SQE motivations:
      • How
        • Improve search results by applying semantic based reasoning
          • Expand queries that have few results, or
          • Narrow number of results when there are to many of them
        • reflect user’s interests in results
    • 5. Algorithm overview:
      • User writes a query
      • Query is processed by the fulltext search engine – Lucene
        • Results are sorted using two metrics: TF(Term Frequency) and
        • IDF(Inverse Document Frequency)
      • Semantic Query Expansion is called
      • Search history is saved for future use
    • 6. SQE picture: Search: Java web Lucene Query Expansion (WordNet,Taxonomies,FOAF) Results (TF/IDF) Java(PL) Java (Island) 60 10 SSCF Bookmarks FOAFRealm Web(www) Spider’s web 50 20 Results History Friends
    • 7. Semantic Query Expansion in details:
      • Giving words meanings
      • Associating weights to results:
        • Long-term context – user’s interests
        • Mid-term context – recent searches, recently browsed resources etc.
        • Short-term context – last queries and query itself
      • Final weight is calculated for each result
      • If results are not sufficient or are to broad expansion is being made, else results are returned
    • 8. Ideas :
      • Word similarity
      • Word meaning in text
      • Allow users to view algorithm steps, and if neccessary, modify them by hand
        • The „Tell me why” button

    ×