1 / 16

CLEF Interactive Track Overview

CLEF Interactive Track Overview. iCLEF. Douglas W. Oard, UMD, USA Julio Gonzalo, UNED, Spain. Outline. Goals Track design Participating teams Results. CLEF. Query. Search. Ranked List. Query. Query Reformulation. iCLEF. Query Formulation. Query Translation. Translated Query.

londonl
Download Presentation

CLEF Interactive Track Overview

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CLEF Interactive Track Overview iCLEF Douglas W. Oard, UMD, USA Julio Gonzalo, UNED, Spain CLEF 2003

  2. Outline • Goals • Track design • Participating teams • Results

  3. CLEF Query Search Ranked List

  4. Query Query Reformulation iCLEF Query Formulation Query Translation Translated Query Search Ranked List Selection Document Examination Document Use

  5. iCLEF Goals • Track design • Component evaluation (since 2001) • End-to-end evaluation (since 2002) • System evaluation • Support for interactive document selection • Support for query creation • Support for iterative refinement

  6. Document Selection Experiments Topic Description Standard Ranked List Interactive Selection F 0.8

  7. End-to-End Experiments Topic Description Query Formulation Automatic Retrieval Interactive Selection Average Precision F 0.8

  8. Topics • Eight “broad” (multifaceted) topics • 1: The Ames espionage case (C100) • 2: European car industry (C106) • 3: Computer security (C109) • 4: Computer animation (C111) • 5: Economic policies of Eduoard Balladur (C120) • 6: Marriage Jackson-Presley (C123) • 7: German armed forces out-of-area (C133) • 8: EU fishing quotas (C139) • Selected from the CLEF 2002 topic set • Not too easy (e.g., proper name not perfectly predictive) • Not too hard (e.g., requiring specialize expertise) • (Relevant documents in every collection?)

  9. Test Collection • Any CLEF-2002 language collection • Systran baseline translations • Spanish to English, English to Spanish • Augmented relevance judgments • Start with CLEF-2002 judgments • Enrich pools with: • Top 20 documents from every iteration • Every document judged by a user • Judge all additions to the pools

  10. Measures of Effectiveness • Query Formulation: Uninterpolated Average Precision • Expected value of precision [over relevant document positions] • Interpreted based on query content at each iteration • Document Selection: Unbalanced F-Measure: • P = precision • R = recall •  = 0.8 favors precision • Models expensive human translation

  11. Variation in Automatic Measures • System • What we seek to measure • Topic • Sample topic space, compute expected value • Topic+System • Pair by topic and compute statistical significance • Collection • Repeat the experiment using several collections

  12. Additional Effects in iCLEF • Learning • Vary topic presentation order • Fatigue • Vary system presentation order • Topic+User (Expertise) • Ask about prior knowledge of each topic

  13. Presentation Order

  14. iCLEF 2003 Research Questions • SICS (Sweden) • What happens when Swedes read English? • Alicante (Spain) • Can NLP-based summaries beat passages? • BBN/Maryland (USA) • Can NLP-based summaries beat passages? • Maryland (USA) • Is user-assisted translation helpful? • UNED (Spain) • Is searching summaries as good as full text? Document Selection End-to-End

  15. 2002 Results

  16. ? Why? 2003 Results

More Related