Automatic Bitext Alignment for Southeast Asian Languages
Here is my Master's thesis on the Automatic Bitext Alignment for Southeast Asian Languages. Bitext corpus is a collection of text in two languages; in this case, English and Thai. I automatically aligned English sentences with their Thai translations. The methodology I proposed here could be used for any Southeast Asian languages, for example, Burmese. I have to post my thesis here because the Asian Institute of Technology does not give people online access to its thesis repository.