Ixa Group is collaborating since 2011 with the UNSAAC university (Cusco, Peru). The main goal of this collaboration is to make use of the experience and know-how acquired in Basque automatic processing and apply it to the processing of Quechua, that is also an agglutinative language like Basque.
We are developing a spelling checker, based on a general purpose morphologic analyzer, as well as a simple syntactic parser. In some months, we will have a first version of a lexical database and a text corpus, both queryable through the web.
Last year we had two fellow visitors:
- Hugo Quispe, who is working on the lexical database, and
- Richard Castro, we has been working with him on the spelling checker and on diverse aspects related to Quechua’s speech processing.
This year, we welcomed two more visitors:
- Rosemary Jimenez, who had presented her master’s thesis on automatic classification of Quechua texts, and that is currently working on the construction of a text corpus and its consultation application; and
- José Lozano, who is working, together with Waldir Farfan, on the development of a teaching system of Quechua (work presented in Poland at the Language Technology Congress, LTC’2013).
These collaboration efforts have been financed by the Spanish Ministry of Cooperation in 2012 and by the University of the Basque Country in 2013 (RUNASIMI project). In Cusco, a team called Hinantin was born, under the supervision of Professor Juan Cruz (UNSAAC). We are currently defining a new project to follow these works in 2014.
[…] RUNASIMI project: processing of Quechua […]