I successfully defended my thesis last Wednesday at the Asian Institute of Technology. My thesis is about bitext alignment for Southeast Asian languages. A bitext corpus is a collection of text in one language with its equivalent translation in another. Bitext corpora are useful for assisting human and machine translations, cross-language information retrieval and language acquisition. I tried to align sentences from several Thai-English bitext corpora. The methodology that I propose can be used to align English with other Southeast Asian languages such as Burmese, Khmer and Lao.
I have been busy with all the stupid requirements for graduating students.