TIAD 2021 – 4th Translation Inference Across Dictionaries – Shared Task & Workshop @ LDK 2021

2ND CALL – NEW DATES & REVIEW COMMITTEE



CALL FOR PARTICIPATION

We are pleased to invite you to participate in the fourth edition of the shared task and workshop for Translation Inference Across Dictionaries (TIAD 2021), which will be held in conjunction with the third Conference on Language, Data and Knowledge (LDK 2021) on September 1, 2021 in Zaragoza, Spain.

This TIAD series is aimed at exploring best methods and techniques for automatically generating new bilingual (and multilingual) lexicographic resources from existing ones, in the context of a coherent experiment that enables reliable validation and solid comparison of results and stimulates further research.

TASK DEFINITION

The objective of the task is to explore and compare methods and techniques to infer translations indirectly between language pairs, based on existing bilingual resources from the Apertium RDF graph (v2.0), which currently includes 53 RDF bilingual dictionary sets across 43 languages. Such techniques would help in auto-generating new bilingual and multilingual dictionaries based on existing ones.

The participating systems are asked to indirectly generate translations among three languages – English, French and Portuguese – based on already known translations contained in the Apertium RDF graph (http://linguistic.linkeddata.es/apertium/), where these languages are not directly connected.

Participants are invited to apply their methods and techniques to discover indirect translations (mediated by any other language in the graph) between the pairs EN/FR, FR/PT and PT/EN, and may also make use of other freely available sources of background knowledge to improve performance, as long as no direct translations among the final language pairs are used.

Evaluation of the results will be carried out against manually compiled pairs from the Global Series of K Dictionaries – Lexicala (https://lexicala.com/resources#dictionaries).

The inclusion of other language pairs or evaluation data by the organisers could be considered, in which case this will be conveniently announced to participants.

PUBLICATION OF RESULTS

Participants will submit a system paper that should include a description of the system, the way the data have been processed, the applied algorithms, the obtained results, and the conclusions and ideas for future improvements. The papers will be peer reviewed prior to publication.

The workshop will accept also regular papers from participants who are not participating in the shared task but still have worked in the domain of translation inference and want to publish novel results or ideas, maybe with different datasets and experimental basis as the ones proposed in this shared task. Such papers will be peer reviewed on the basis of their scientific quality.

All the accepted papers will be published in the TIAD workshop part of LDK 2021 Proceedings.

TIAD 2021 will consist of a half-day tutorial with oral presentations by participants describing their systems and by the organizers describing the overall results, followed by a concluding panel (with all the presenters) on lessons learnt and future steps.

SUBMISSION

Please see the TIAD 2021 website for formatting and submission instructions.

As the reviewing process is single-blind, submissions should not be anonymized.

At least one author of each accepted paper must register to LDK 2021 to present the paper at the workshop.

COVID-19

If the epidemiological situation and travel restrictions do not allow for a physical event, TIAD 2021 will be held virtually, in which case the format may change to accommodate the specifics of online events. Proceedings will be published in either case.

IMPORTANT DATES (2021)

February 1. Technical description of evaluation process and data provided by the organisers
April 23. Submission of regular papers (not participating systems)
May 14. Submission of results by participating systems / notification of regular papers
June 14. Evaluation results communicated by organisers / camera–ready of regular papers
July 9. Submission of system description papers
September 1. TIAD 2021 workshop day

ORGANISERS

Jorge Gracia. University of Zaragoza, Spain
Besim Kabashi. Friedrich Alexander University of Erlangen-Nuremberg & Ludwig Maximilian University of Munich, Germany
Ilan Kernerman. K Dictionaries – Lexicala, Tel Aviv, Israel
Noam Ordan. University of Haifa, Israel

REVIEW COMMITTEE

Omri Abend, Hebrew University of Jerusalem, Israel
Sina Ahmadi, National University of Ireland Galway, Ireland
Julia Bosque-Gil, University of Zaragoza, Spain
Thierry Declerck, DFKI, Germany
Jorge Gracia, University of Zaragoza, Spain
Dagmar Gromann, University of Vienna, Austria
Yinxia Huang, Pai Chai University, South Korea
Besim Kabashi, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
Ilan Kernerman, K Dictionaries – Lexicala, Israel
Fahad Khan, Istituto di Linguistica Computazionale "Antonio Zampolli", Italy
Simon Krek, Jožef Stefan Institute, Slovenia
Maite Melero, Barcelona Supercomputing Center, Spain
Elena Montiel-Ponsoda, Universidad Politécnica de Madrid, Spain
Noam Ordan, University of Haifa, Israel
Georg Rehm, DFKI, Germany
Artem Revenko, Semantic Web Company, Austria
Arvi Tavast, Estonian Language Institute, Estonia
Andrzej Zydroń, XTM International, UK

WEBSITE

https://tiad2021.unizar.es/

SUPPORTED BY

GlobaLex (Global Alliance for Lexicography) https://globalex.link/
EMLex (European Master in Lexicography) https://emlex.phil.fau.eu/
NexusLinguarum (European network for Web-centred linguistic data science) https://nexuslinguarum.eu/
Prêt-à-LLOD https://pret-a-llod.eu/