IberEval 2018
*** Full program of the IberEval workshop is already available ***
IberEval 2018 aims at encouraging and promoting the development of Human Language Technologies (HLT) for Iberian languages (Spanish, Portuguese, Catalan, Basque and Galician), by creating series of evaluation and a discussion forum about Natural Language Processing systems on an ongoing basis.
This third IberEval workshop will be held together with SEPLN 2018 in Seville, Spain, on September 18.
Tracks
• Authorship and aggressiveness analysis in Twitter: case study in Mexican Spanish (MEX-A3T)
• Automatic Misogyny Identification (AMI)
• Second Biomedical Abbreviation Recognition and Resolution track (BARR2)
• Disability annotation on documents from the biomedical domain (DIANN)
• Humor Analysis based on Human Annotation (HAHA)
• MultiModal Stance Detection in tweets on Catalan 1Oct Referendum (MultiStanceCat)
Important Dates
14 Jan 2018: Task proposals due [passed]
31 Jan 2018: Notifications of task acceptance [passed]
02 Jul 2018: Camera ready submissions due
18 Sep 2018: IberEval Workshop
Call for Track Proposals (passed)
Researchers and practitioners from all areas of Natural Language Processing and related communities are invited to submit proposals for evaluation tasks on computational problems that involve text processing in at least one of the following Iberian languages: Spanish, Portuguese, Catalan, Basque and Galician. The outcome of accepted tasks will be discussed in the IBEREVAL workshop to be held in conjunction with SEPLN 2018 in Seville (Spain) in September.
Two types of proposals are expected:
- Standard evaluation campaigns in the style of TREC, CLEF, SemEval, NTCIR, or FIRE evaluation exercises.
- More exploratory initiatives that aim to settle the foundations for future evaluation campaigns, discussing tasks, methodologies, metrics, test collections, etc.
Proposals should include the following information:
- Title of the track.
- Name(s) of organizers and contact details, with one-paragraph statements of their research interests, areas of expertise, and experience in organizing related events.
- Brief description of the task goal, including their significance for the field and the expected target audience.
- Arrangements for the organization of the task: who will be responsible for which activities, description of the data or how will data be acquired or created, available funding, proposed schedule, and any other relevant issues.
Proposals must be submitted to:
ibereval2018organizers@listserv.uned.es
We strongly encourage the Latin America NLP research community to organize tasks and participate in IberEval campaigns.
Task Selection
Each submitted proposal will be reviewed by the IBEREVAL steering committee, and decisions will be sent to organizers by January 31, 2018. At least one of the organizers of each accepted track is expected to attend the IBEREVAL workshop and present the results of the track.