CLC & CDLD 2014: Summary and Results

Beween August 11th and August 23rd 2014 CIDLeS, together with 10 volunteers, organized two summer schools at Quinta da Malgueira in Minde (Portugal), which were attended by more than 70 participants from all over the world.

The first week (August 11th – August 15th) was dedicated to Coding for Language Communities (CLC 2014).

(Talk by Bruce Birch)

It counted with the participation of 25 students/researchers, who were mentored by Kevin Scannell (Saint Louis University, USA), Bruce Birch (The Australian National University, Australia), Peter Grasch (Open Speech Initiative, Austria), Pavel Mihaylov (Bulgaria), and Dorothee Beermann (Norwegian University of Science and Technology/Trondheim, Norway). They have also received special training in workshops about multi-platform user interaction (by Luís Marcelino, Instituto Politécnico de Leiria), Python (João Oliveira, Lisbon), tools for collaborative work (Ricardo Filipe and Pedro Manha, CIDLeS), FST technology (Iñaki Alegria, IXA group at the University of the Basque Country), and open source NLP tools (José Ramom Pichel, imaxin software).

The abstracts and slides of the talks and workshops can be consulted the links below. The videos of the talks will be published soon.


(The participants working on their projects with the mentors)

Students, researchers, mentors, and speakers work together on the development of computational tools for minority and/or endangered languages. Together with their mentors, the participants developed several projects which they presented at the end of the summer school, namely:

– Fala Dictionary
– Amharic Twitter extraction and spell checker
– Finding near matches for spell checker development (Haitian Creole and Sylhet)
– Real time language twitter map
– Roma Dictionary 
– Cotu (Eastern Katu) Dictionary in Typecraft
– Speech Modelling using SIMON
– Buryad spell checker

Detailed information about the projects developed at CLC 2014 can be consulted here:

At the end, all the participants selected what they considered the best project of CLC 2014 and the winner was Roma Dictionary by Benoit Legouy, Pedro Manha, Eleni Ntalambyra Elodie Paquette, Claire Ulrich, Ricardo Filipe, and Rosana Margarida, mentored by Bruce Birch.

(The winning project – Roma Dictionary)

More CLC photos in

The second week (August 18th – August 23rd) was dedicated to Community-Driven Language Documentation (CDLD 2014). The international summer school was intended to be a space for engagement and exchange between community members, language workers and students and provide an environment for learning about each other’s interests and requirements. The aim was achieved!

(CDLD participants at Quinta da Malgueira)

30 participants, together with 10 lecturers, had the opportunity to experience a very interdisciplinary week, with courses not only on “traditional” subjects of language documentation (audio & video recordings, annotations, lexicography, revitalization) but also on related disciplines (ethnobotany and ethnomusicology). The videos of the talks will be published soon.

(Fieldwork on ethnobotany with Ana Maria Carvalho)

A very detailed report and evaluation of CDLD written by Carmen Alegria, one of the participants of the summer school, can be consulted here:

More CDLD photos in

Thank you to all the participants, mentors, trainers and lecturers who attended CLC & CDLD for your ethusiasm and for making it such an awesome event! A special thanks to our sponsors and partners for making the summer schools possible.

Sponsors and Partners



Looking forward to meeting you next year!

Leave a Reply