1 / 15

The INFILE project: a crosslingual filtering systems evaluation campaign

The INFILE project: a crosslingual filtering systems evaluation campaign. Romaric Besançon , Stéphane Chaudiron, Djamel Mostefa, Ismaïl Timimi, Khalid Choukri. Overview. Goals and features of the INFILE campaign Test collections: Documents Topics Assessments Evaluation protocol

avery
Download Presentation

The INFILE project: a crosslingual filtering systems evaluation campaign

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. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit The INFILE project: a crosslingual filtering systems evaluation campaign Romaric Besançon , Stéphane Chaudiron, Djamel Mostefa, Ismaïl Timimi, Khalid Choukri

  2. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Overview • Goals and features of the INFILE campaign • Test collections: • Documents • Topics • Assessments • Evaluation protocol • Evaluation procedure • Evaluation metrics • Conclusions

  3. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Goals and features of the INFILE Campaign • Information Filtering Evaluation • filter documents according to long-term information needs (user profiles - topics)‏ • Adaptive : use simulated user feedback • Following TREC adaptive filtering task • Crosslingual • three languages: English, French, Arabic • close to real activity of competitive intelligence professionals • in particular, profiles developed by CI professional (STI)‏ • pilot track in CLEF 2008

  4. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Test Collection • Built from a corpus of news from the AFP (Agence France Presse)‏ • almost 1.5 million news in French, English and Arabic • For the information filtering task: • 100 000 documents to filter, in each language • NewsML format • standard XML format for news (IPTC)‏

  5. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Document example document identifier keywords headline

  6. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Document example IPTC category AFP category location content

  7. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Profiles • 50 interest profiles • 20 profiles in the domain of science and technology • developped by CI professionals from INIST, ARIST, Oto Research, Digiport • 30 profiles of general interest

  8. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Profiles • Each profile contains 5 fields: • title: a few words description • description: a one-sentence description • narrative: a longer description of what is considered a relevant document • keywords: a set of key words, key phrases or named entities • sample: a sample of relevant document (one paragraph)‏ • Participants may use any subset of the fields for their filtering

  9. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Constitution of the corpus • To build the corpus of documents to filter: • find relevant documents for the profiles in the original corpus • use a pooling technique with results of IR tools • the whole corpus is indexed with 4 IR engines (Lucene, Indri, Zettair and CEA search engine)‏ • each search engine is queried independently using the 5 different fields of the profiles + all fields + all fields but the sample • 28 runs

  10. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Constitution of the corpus (2)‏ • pooling using a “Mixture of Experts” model • first 10 documents of each run is taken • first pool assessed • a score is computed for each run and each topic according to the assessments of the first pool • create next pool by merging runs using a weighted sum • weights are proportional to the score • ongoing assessments • keep all documents assessed • documents returned by IR systems by judged not relevant form a set of difficult documents • choose random documents (noise)‏

  11. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Evaluation procedure • One pass test • Interactive protocol using a client-server architecture (webservice communication)‏ • participant registers • retrieves one document • filters the document • ask for feedback (on kept documents)‏ • retrieves new document • limited number of feedbacks (50)‏ • new document available only if previous one has been filtered

  12. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Evaluation metrics • Precision / Recall/F-measure • Utility (from TREC)‏ P=a/a+b R=a/a+c F=2PR/P+R u=w1∗a-w2∗b

  13. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Evaluation metrics (2)‏ • Detection cost (from TDT)‏ • uses probability of missed documents and false alarms

  14. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Evaluation metrics • per profile and averaged on all profiles • adaptivity: score evolution curve (values computed each 10000 documents)‏ • two experimental measures • originality • number of relevant documents a system uniquely retrieves • anticipation • inverse rank of first relevant document detected

  15. LIST – DTSI – Interfaces, Cognitics and Virtual Reality Unit Conclusions • INFILE campaign • Information Filtering Evaluation: • adaptive, crosslingual, close to real usage • Ongoing pilot track in CLEF 2008 • current constitution of the corpus • dry run mid-June • evaluation campaign in July • workshop in September • Work in progress • the modelling of the filtering task assumed by the CI practitioners

More Related