[Corpora-List] Deadline Extended: IBEREVAL 2017 - Task: Multilingual Web Person Name Disambiguation

Richard Berendsen richard.berendsen at luminis.eu
Fri Apr 21 14:59:38 CEST 2017


Please consider contributing and/or forwarding to appropriate

colleagues and groups. *******We apologize for the multiple copies of this e-mail******

---------------------------------------------- Deadline Extended Notice ----------------------------------------------

Multilingual Web Person Name Disambiguation (M-WePNaD) task at IBEREVAL 2017 Webpage: http://nlp.uned.es/IberEval-2017/index.php/Tasks/M-WePNaD

held in conjunction with the SEPLN 2017 <http://sepln2017.um.es/en_version/index.html> International conference 19th September 2017, University of Murcia, Murcia (Spain)

----------------------------------------------

This task focuses on the disambiguation of person names in web search results for person name queries. The search results are realistic web search results; they: are multilingual, include social media profiles, include pages that contain no reference to the person name query, and vary in the number of unique referents. This poses interesting additional challenges to earlier tasks like WePS-1, WePS-2, and WePS-3.

The organisers have compiled a corpus of 100 queries, annotated by three experts. A random sample of 65 of these queries has been released as a training set Monday, March 13th, 2017. Participants still have three weeks to develop their disambiguation algorithms. On Monday, May 12th, 2017, the 35 remaining test queries will be released, without annotations. Participants are requested to submit runs on test data at May 16th, 2017, and a working notes paper on Thursday, Jun 5th, 2017. The organizers will evaluate the performance of the participants, and put together a ranked list of systems. Final results of this task will be presented and discussed as part of the IberEval 2017 workshop. See the task website for details on the training corpus, how to download it, how runs will be evaluated, and for the performance scores of two basic clustering algorithms on the training set.

We cordially invite all researchers and practitioners from all fields to participate in this task: Multilingual Web Person Name Disambiguation. We also invite the participants to subscribe to our Google mailing list in order to be kept up to date with the latest news, tips, and tricks related to the task: m-wepnad at googlegroups dot com. To receive updates on Twitter, follow our account @mwepnad2017<https://twitter.com/mwepnad2017>

---------------------------------------------- Important Dates ----------------------------------------------

[13 Mar, 2017: Training set released.] 12 May, 2017: Test set released. 16 May, 2017: Deadline for submission of results. 22 May, 2017: Competition results announced. 05 Jun, 2017: Deadline for participants to submit Working notes. 15 Jun, 2017: Reviews of Working notes sent out to authors. 01 Jul, 2017: Deadline to submit revised Working notes. 19 Sep, 2017: Workshop at SEPLN 2017.

---------------------------------------------- Track Coordinators ----------------------------------------------

Soto Montalvo (URJC, Móstoles, Madrid, Spain) Raquel Martínez (UNED, Madrid, Spain) Víctor Fresno (UNED, Madrid, Spain) Agustín D. Delgado (UNED, Madrid, Spain) Arkaitz Zubiaga (University of Warwick, England) Richard Berendsen (Luminis Amsterdam, The Netherlands)

---------------------------------------------- Contact ----------------------------------------------

E-mail: m-wepnadorganizers at listserv.uned.es<http://listserv.uned.es> Track Web page: http://nlp.uned.es/IberEval-2017/index.php/Tasks/M-WePNaD Twitter: M-WePNaD on Twitter: @mwepnad2017<https://twitter.com/mwepnad2017> -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 22821 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20170421/8b0c7a85/attachment.txt>



More information about the Corpora mailing list