![]() ![]() The six lines in yellow are the Huggingface API, which allow me to access Microsoft’s Marian Neural Machine Translation models, and have them use the pretrained models generated by the University of Helsinki. ![]() I open a database, get some lines, manipulate them, and put them back. It looks a lot like code I’ve written over the years. To understand why, it helps to look at the code: This translation program is entirely different. It wasn’t always true in practice, but the idea was conceptually sound. That’s the idea that you can, if you have the time and skills, step through a program line by line in a debugger and figure out what’s going on. See, I’ve been programming since the late 1970’s, in many, many, languages and environments, and the common thread in everything I’ve done was the idea of deterministic execution. I think I’m seeing the power and risks of AI/ML in this tiny example. It’s still chunking along, and has translated over 27,000 tweets so far. To expand the range of analytic tools that can be used, and to open up the dataset for non-Arabic speakers (like me!), I wrote a ML-based translation program, and fired it up yesterday morning. So far we’ve downloaded over 100,000 tweets. One of the projects I’ve been working on is a study on COVID-19 misinformation in Saudi Arabia.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |