Advances in cross-language information retrieval : Third Workshop of the Cross-Language Evaluation Forum, CLEF 2002, Rome, Italy, September 19-20, 2002 : revised papers

This book presents the thoroughly refereed post-proceedings of a workshop by the Cross-Language Evaluation Forum Campaign, CLEF 2002, held in Rome, Italy in September 2002. The 43 revised full papers presented together with an introduction and run data in an appendix were carefully reviewed and revised upon presentation at the workshop. The papers are organized in topical sections on systems evaluation experiments, cross language and more, monolingual experiments, mainly domain-specific information retrieval, interactive issues, cross-language spoken document retrieval, and cross-language evaluation issues and initiatives. The Third Campaignof The Cross-languageevaluation Forum (clef) For Eu- Pean Languages Was Held From January To September 2002. Participation In This Campaignshowedaslightriseinthenumberofparticipantswith,37groupsfrom Both Academia And Industry And A Steep Rise In The Number Of Experiments They Submitted For Oneor Moreof The ?ve O?cialtracks. The Campaignculminated In Atwo-dayworkshopheldinrome,italy,19–20september,immediatelyfollowing The Sixth European Conference On Digital Libraries (ecdl 2002), Attended By Nearly 70 Researchersand System Developers. The Objective Of The Workshop Was To Bring Together The Groups That Had Participated In Clef 2002 So That They Could Report On The Results Of Their Experiments. Attendance At The Workshop Was Thus Limited To Participants In The Campaignplus Severalinvited Guests With Recognized Expertise In The Multilingual Information Access ?eld. This Volume Contains Thoroughly Revised And Expanded Versions Of The Preliminary Papers Presented At The Workshop Accompanied By A Complete Run-down And Detailed Analysis Of The Results, And It Thus Provides An Exhaustive Record Of The Clef 2002 Campaign. Clef2002 Wasconducted Within The Frameworkof A Projectof The Infor- Tion Society Technologies Programme Of The European Commission (ist-2000- 31002). The Campaign Was Organized In Collaboration With The Us National - Stitute Ofstandardsandtechnology(nist)andwiththe Supportofthedelos Network Of Excellence For Digital Libraries. The Support Of Nist And Delos In The Running Of The Evaluation Campaign Is Gratefully Acknowledged. We Would Also Like To Thank The Other Members Of The Workshop Steering Committee For Their Assistance In The Coordination Of This Event. I System Evaluation Experiments At Clef 2002 -- Clef 2002 – Overview Of Results -- Cross-language Retrieval Experiments At Clef 2002 -- Itc-irst At Clef 2002: Using N-best Query Translations For Clir -- Océ At Clef 2002 -- Report On Clef 2002 Experiments: Combining Multiple Sources Of Evidence -- Utaclir @ Clef 2002 – Bilingual And Multilingual Runs With A Unified Process -- A Multilingual Approach To Multilingual Information Retrieval -- Combining Evidence For Cross-language Information Retrieval -- Exeter At Clef 2002: Experiments With Machine Translation For Monolingual And Bilingual Retrieval -- Portuguese-english Experiments Using Latent Semantic Indexing -- Thomson Legal And Regulatory Experiments For Clef 2002 -- Eurospider At Clef 2002 -- Merging Mechanisms In Multilingual Information Retrieval -- Sinai At Clef 2002: Experiments With Merging Strategies -- Cross-language Retrieval At The University Of Twente And Tno -- Scalable Multilingual Information Access --^ Some Experiments With The Dutch Collection -- Resolving Translation Ambiguity Using Monolingual Corpora -- Experiments In 8 European Languages With Hummingbird Searchservertm At Clef 2002 -- Italian Monolingual Information Retrieval With Prosit -- Cole Experiments In The Clef 2002 Spanish Monolingual Track -- Improving The Automatic Retrieval Of Text Documents -- Ir-n System At Clef-2002 -- Experiments In Term Expansion Using Thesauri In Spanish -- Sics At Clef 2002: Automatic Query Expansion Using Random Indexing -- Pliers And Snowball At Clef 2002 -- Experiments With A Chunker And Lucene -- Information Retrieval With Language Knowledge -- Domain Specific Retrieval Experiments With Mimor At The University Of Hildesheim -- Using Thesauri In Cross-language Retrieval Of German And French Indexed Collections -- Assessing Automatically Extracted Bilingual Lexicons For Clir In Vertical Domains: Xrce Participation In The Girt Track Of Clef 2002 -- The Clef 2002 Interactive Track --^ Sics At Iclef 2002: Cross-language Relevance Assessment And Task Context -- Universities Of Alicante And Jaen At Iclef -- Comparing User-assisted And Automatic Query Translation -- Interactive Cross-language Searching: Phrases Are Better Than Terms For Query Formulation And Refinement -- Exploring The Effect Of Query Translation When Searching Cross-language -- Clef 2002 Cross-language Spoken Document Retrieval Pilot Track Report -- Exeter At Clef 2002: Cross-language Spoken Document Retrieval Experiments -- Cross-language Spoken Document Retrieval On The Trec Sdr Collection -- Ii Cross-language Systems Evaluation Initiatives, Issues And Results -- Clir At Ntcir Workshop 3: Cross-language And Cross-genre Retrieval -- Linguistic And Statistical Analysis Of The Clef Topics -- Clef 2002 Methodology And Metrics. Carol Ann Peters ... [et Al.] (eds.) Includes Bibliographical References And Index. Front Matter....Pages I-XI Introduction....Pages 1-5 Front Matter....Pages 7-7 CLEF 2002 — Overview of Results....Pages 9-27 Cross-Language Retrieval Experiments at CLEF 2002....Pages 28-48 ITC-irst at CLEF 2002: Using N -Best Query Translations for CLIR....Pages 49-58 Océ at CLEF 2002....Pages 59-65 Report on CLEF 2002 Experiments: Combining Multiple Sources of Evidence....Pages 66-90 UTACLIR @ CLEF 2002 — Bilingual and Multilingual Runs with a Unified Process....Pages 91-100 A Multilingual Approach to Multilingual Information Retrieval....Pages 101-110 Combining Evidence for Cross-Language Information Retrieval....Pages 111-126 Exeter at CLEF 2002: Experiments with Machine Translation for Monolingual and Bilingual Retrieval....Pages 127-146 Portuguese-English Experiments Using Latent Semantic Indexing....Pages 147-154 Thomson Legal and Regulatory Experiments for CLEF 2002....Pages 155-163 Eurospider at CLEF 2002....Pages 164-174 Merging Mechanisms in Multilingual Information Retrieval....Pages 175-186 SINAI at CLEF 2002: Experiments with Merging Strategies....Pages 187-196 Cross-Language Retrieval at the University of Twente and TNO....Pages 197-206 Scalable Multilingual Information Access....Pages 207-218 Some Experiments with the Dutch Collection....Pages 219-222 Resolving Translation Ambiguity Using Monolingual Corpora....Pages 223-241 Experiments in 8 European Languages with Hummingbird SearchServerTM at CLEF 2002....Pages 242-256 Front Matter....Pages 7-7 Italian Monolingual Information Retrieval with PROSIT....Pages 257-264 COLE Experiments in the CLEF 2002 Spanish Monolingual Track....Pages 265-278 Improving the Automatic Retrieval of Text Documents....Pages 279-290 IR-n System at CLEF-2002....Pages 291-300 Experiments in Term Expansion Using Thesauri in Spanish....Pages 301-310 SICS at CLEF 2002: Automatic Query Expansion Using Random Indexing....Pages 311-320 Pliers and Snowball at CLEF 2002....Pages 321-335 Experiments with a Chunker and Lucene....Pages 336-337 Information Retrieval with Language Knowledge....Pages 338-342 Domain Specific Retrieval Experiments with MIMOR at the University of Hildesheim....Pages 343-348 Using Thesauri in Cross-Language Retrieval of German and French Indexed Collections....Pages 349-362 Assessing Automatically Extracted Bilingual Lexicons for CLIR in Vertical Domains: XRCE Participation in the GIRT Track of CLEF 2002....Pages 363-371 The CLEF 2002 Interactive Track....Pages 372-382 SICS at iCLEF 2002: Cross-Language Relevance Assessment and Task Context....Pages 383-391 Universities of Alicante and Jaen at iCLEF....Pages 392-399 Comparing User-Assisted and Automatic Query Translation....Pages 400-415 Interactive Cross-Language Searching: Phrases Are Better than Terms for Query Formulation and Refinement....Pages 416-429 Exploring the Effect of Query Translation when Searching Cross-Language....Pages 430-445 CLEF 2002 Cross-Language Spoken Document Retrieval Pilot Track Report....Pages 446-457 Exeter at CLEF 2002: Cross-Language Spoken Document Retrieval Experiments....Pages 458-475 Front Matter....Pages 7-7 Cross-Language Spoken Document Retrieval on the TREC SDR Collection....Pages 476-481 Front Matter....Pages 483-483 CLIR at NTCIR Workshop 3: Cross-Language and Cross-Genre Retrieval....Pages 485-504 Linguistic and Statistical Analysis of the CLEF Topics....Pages 505-511 CLEF 2002 Methodology and Metrics....Pages 512-525 Back Matter....Pages 527-832