[Corpora-List] [Call for Participation] DIACR-Ita - Diachronic lexical semantics in Italian task at EVALITA 2020 (REVISED timetable)

Annalina Caputo annalina.caputo at dcu.ie
Tue Aug 18 17:39:23 CEST 2020


==== REVISED timetable (apologies for cross-posting) ====

*EVALITA-2020: Diachronic lexical semantics in Italian*

Shared Task Website: https://diacr-ita.github.io/DIACR-Ita/ Email: diacrita.evalita at google.com Registration: http://www.evalita.it/2020/taskregistration Google Groups: https://groups.google.com/d/forum/evalita-2020-diacr-ita

Researchers and industry professionals are invited to participate in the first shared task on diachronic lexical semantics in Italian (DIACR-Ita) organised within Evalita 2020, the 7th evaluation campaign of Natural Language Processing and Speech tools for Italian, which will be held in Bologna (Italy) and will be co-located with CLiC-it 2020 (November 30th – December 3rd 2020).

DIACR-Ita is the first task on lexical semantic change for Italian, combining together computational and historical linguistics. The task challenges participants to develop systems that can automatically detect if a given word has changed its meaning over time, given contextual information from corpora.

DIACR-Ita builds independently on the Semeval 2020 Task 1: Unsupervised Lexical Semantic Change Detection (Schlechtweg et al. 2020, https://competitions.codalab.org/competitions/20948) that hosted for the first time a task on unsupervised lexical semantic change detection.

---- *Task Description* ----

The goal of the task is to establish if a set of (target) words change their meaning across two periods, t1 and t2, where t1 precedes t2. Following the SemEval 2020 Task 1 setting, we rely on the comparison of two time periods. In this way we tackle two issues: 1) we reduce the number of time periods for which data has to be annotated; 2) we reduce the task complexity, allowing different model architectures to be applied to it, widening the range of possible participants.

Participants will be provided with two corpora C1 and C2 (for time periods t1 and t2, respectively), and a set of target words. For each of them, systems have to decide whether a word changed or not its meaning between t1 and t2 according to the occurrences of the target word(s) in sentences in C1 and C2. For instance, the meaning of the word “imbarcata” is known to have expanded (i.e, it has acquired a new sense) from t1 to t2 (originally it refers to an acrobatic manoeuvre of aeroplanes, but nowadays it is also used to refer to the state of being deeply in love with someone.) This will be reflected in different occurrences of use in sentences between C1 and C2.

The task is formulated as a closed task (i.e., participants must train their models on the data that are provided).

---- *Important Dates (REVISED)* ----

29th May 2020: Distribution of data sets for training and development 4th September 2020: Registration closes 11th September 2020: Distribution of data sets for testing 18th - 25th September 2020: Evaluation windows and collection of participants results 2nd October 2020: Assessment returned to participants 16th October: deadline for submission of system description papers 16th December - 17th December 2020: EVALITA 2020 (http://www.evalita.it/)

---- *Organising Committee* ----

Pierpaolo Basile - Università di Bari “A. Moro” Tommaso Caselli - Rijksuniveristeit Gronigen Annalina Caputo - Dublin City University Rossella Varvara - Università di Firenze Pierluigi Cassotti - Università di Bari “A. Moro”

-- *Annalina Caputo* Academic Lead for MSc in Artificial Intelligencefor ICT Skillnet Assistant Professor | School of Computing | Dublin City University annalina.caputo at dcu.ie | + 353 1 700 8056

School of Computing | Room L2.48 | McNulty Building | Dublin City University | Glasnevin | Dublin 9

-- *

*Séanadh Ríomhphoist/Email Disclaimer*

*Tá an ríomhphost seo agus aon chomhad a sheoltar leis faoi rún agus is lena úsáid ag an seolaí agus sin amháin é. Is féidir tuilleadh a léamh anseo.  <https://sites.google.com/view/seanadh-riomhphoist>*

*This e-mail and any files transmitted with it are confidential and are intended solely for use by the addressee. Read more here. <https://sites.google.com/view/dcu-email-disclaimer>*

*

--

<https://www.facebook.com/DCU/> <https://twitter.com/DublinCityUni> <https://www.linkedin.com/company/dublin-city-university> <https://www.instagram.com/dublincityuniversity/?hl=en> <https://www.youtube.com/user/DublinCityUniversity> -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 9877 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20200818/aa4bbf45/attachment.txt>



More information about the Corpora mailing list