(Please excuse cross-postings.)
TIAD 2017 Shared Task: Translation Inference Across Dictionaries
2nd Call for participation - Review Committee announced
https://tiad2017.wordpress.com
Overview
Various methods and techniques have been explored in the past in the aim of
automatically generating new bilingual (and multilingual) dictionaries from
existing ones, for instance using one (or more) language(s) as a pivot between
two other source and target languages. However, such efforts were usually
conducted on different types of datasets and evaluated in different ways,
making it difficult to compare due to the different experimental setups and
evaluation metrics.
TIAD-2017 is launched with the intention of offering quality lexical resources
for a coherent experiment that enables reliable validation of results and solid
comparison of methods and techniques used for the automatic generation of
translations across languages. This initiative aims also to stimulate and
enhance further research on the topic. It will make use of cross-lingual
lexicographic data of K Dictionaries (KD), which will serve also to validate
the results along with human assessment. The systems developed by participants
and their results will be presented at a workshop that will be held as part of
the first Language, Data and Knowledge conference in Galway, Ireland, on 18
June 2017 (http://ldk2017.org). The papers describing the participant systems
will be published on CEUR-WS (http://ceur-ws.org).
Task definition
The objective of the task is to indirectly generate translations for three
language pairs, based on already known translations among eight languages in 14
bilingual dictionaries, involving four possible paths - all from German to
Brazilian Portuguese - that feature between 1 to 4 pivot languages.
The test dataset consists of 100 randomly-selected German dictionary entries
with their translations into a second language, and recursively exploring
further translations in chained-up dictionaries - including up to 817 entries
with 1,532 translation equivalents in the largest language pair that is
provided. Besides the headwords and translations, the data includes information
about the parts of speech, subject domains and synonyms, as well as examples of
usage and their translations.
The following language pairs are provided for the four paths:
(a) German > English > Portuguese
(b) German > Japanese > Spanish > Portuguese
(c) German > Danish > French > Spanish > Portuguese
(d) German > Dutch > Spanish > Danish > French > Portuguese
Also included are four Portuguese > German datasets, for closing the loop in
each path, to help with the validation of the results.
The three new language pairs that should be generated are:
(1) German > Portuguese
(2) Danish > Spanish
(3) Dutch > French
Evaluation of the results of each system will be carried out against KD's
manually compiled dictionaries for these pairs from the Global Series and other
resources, as well as by human translators.
Participants can contribute on either or both of the following tracks:
(1) Systems that use only the KD data released for the task
(2) Systems that exploit, in addition to the KD data, other freely available
sources of background knowledge (e.g., lexical linked open data and parallel
corpora) to improve performance
Beyond performance, participants are encouraged to consider the following
issues in particular:
* The role of the language family with respect to the newly generated
pairs
* The asymmetry of pairs, and how translation direction affects the
results
* The behavior of different parts-of-speech among different languages
* The role the number of pivots plays in the process
Important Dates
* 23.1.2017 - Call for participation / Test data released
* 15.4.2017 - Submission of results by participants
* 30.4.2017 - Evaluation of results communicated by organizers
* 01.6.2017 - Submission of system description papers
* 18.6.2017 - Workshop
Organizers
* Jorge Gracia, Ontology Engineering Group, Universidad Politécnica de
Madrid
* Noam Ordan, K Dictionaries and The Arab Academic College of
Education, Haifa
* Ilan Kernerman, K Dictionaries, Tel Aviv
Review Committee
Irith Ben-Arroyo Hartman, University of Haifa, Israel
Thierry Declerck, German Research Center for Artificial Intelligence, Germany
Thierry Fontenelle, Translation Center for the Bodies of the EU, Luxembourg
Mikel Forcada, Universidad de Alicante, Spain
Jorge Gracia, Universidad Politécnica de Madrid, Spain
Miloš Jakubíček, Lexical Computing, Czech Republic
Jelena Kallas, Institute of the Estonian Language, Estonia
Ilan Kernerman, K Dictionaries, Israel
Iztok Kosem, Trojina Institute and University of Ljubljana, Slovenia
Nikola Ljubešić, University of Zagreb, Croatia
Shervin Malmasi, Harvard University, USA
John McCrae, National University of Ireland, Galway
Elena Montiel-Ponsoda, Universidad Politécnica de Madrid, Spain
Preslav Nakov, Hamad Bin Khalifa University, Qatar
Noam Ordan, K Dictionaries and The Arab Academic College of Education, Israel
Georg Rehm, German Research Center for Artificial Intelligence, Germany
Victor Rodriguez-Doncel, Universidad Politécnica de Madrid, Spain
Liling Tan, Nanyang Technological University, Singapore
Carole Tiberius, Institute of Dutch Language, Netherlands
Marta Villegas, Spain
Marcos Zampieri, University of Köln, Germany
Terms and Website
A full description of TIAD-2017 and its binding terms and regulations are
available on the website: https://tiad2017.wordpress.com.
Contact
Noam Ordan: noam@xxxxxxxxxxxxxxxxx<mailto:noam@xxxxxxxxxxxxxxxxx>
