Columnist's note: The use of computers has become inevitable in the contemporary world. From simple everyday chores to sophisticated high-level tasks, computers will have to be part of the process. It is with great delight then that I am working with the brilliant Jasper Kyle Catapang, who, prior to doing linguistics, was very much involved in computing in the Philippines both in the academia and the industry. He has produced an enviable portfolio of work involving computers. I recently welcomed him to my university as a doctoral researcher in our project with the Oxford English Dictionary, and he is using computational approaches in investigating lexical innovations in Asian Englishes. In this article, he comments on computational resources on Philippine languages.
FOR years, Philippine languages, including Tagalog, Cebuano, Ilocano, Hiligaynon and Waray, have been classified as low-resource languages by the research community of natural language processing (NLP) — the field concerned with the computational analysis of human language. This puts into question how these languages are going to be operationalized in artificial intelligence (AI), given that this somewhat suggests that there is little digital information and linguistic material in these languages. However, this does not paint the whole picture. The Philippines has 186 languages with a unique oral history, literature and culture. A better term might be "latent-resource" languages — lacking computational analysis and awaiting NLP research and development investments to reveal their potential.
Continue reading with one of these options:
Ad-free access
P 80 per month
(billed annually at P 960)
- Unlimited ad-free access to website articles
- Limited offer: Subscribe today and get digital edition access for free (accessible with up to 3 devices)