So cool to see these familiar (virtual) faces over here!! @jordyvl @pdelobelle @nlptown @thomaswint @KarelDO @Sofie
You guessed it, my name is Bram. Did masters in computational linguistics and one in AI (both KU Leuven), and received my PhD this year (Ghent University). I’ve mostly focused on the intersection of computational/psycho- linguistics, human/machine translation, and broader NLP. For the time being I am a post-doc at Ghent University with a focus on human and machine translation.
It is an obvious suggestion that I use transformers in work on MT (Vaswani et al. ^TM). However, I have also been using and training models for very niche tasks, e.g. humor detection. Most recently I employed RoBERTa to predict for tokens how difficult they would be to translated. “Difficulty” here is operationalized as normalized translation duration, and is heavily inspired by psycholinguistic studies. I’ve used Transformer models to train my own spaCy-backed Universal Dependencies models, too - which is not necessary anymore as they are provided out of the box these days. Awesome! Oh, and I am a big Tolkien-nerd so I’ve done some experiments with training a GPT-J-like language model on all the collected work of Tolkien
transformers since the
pytorch_pretrained_bert days and I’ve been trying my best to contribute and help when I can ever since! (In other NLP-related tools as well.)
I think I’m already in touch with most of you, but feel free to shoot me a message or connect on other platforms!
A bit of selling-out about useful conferences and network opportunities in Dutch NLP, in addition to the NLP meetings of @nlptown - which I really haven’t attended and I feel ashamed :
Some of you were present, but I’d like to highlight this here as well: earlier this year we (UGent NLP) organized the CLIN conference (computational linguistics in the Netherlands), which is getting bigger every year. I am currently also guest editor for the follow-up journal that comes out of this conference, and we’re so happy with the interest that we have received. If you are eager about NLP/compling, please do join us at the next CLIN conference! I think it’s at Tilburg University next year (It’s at a different Dutch/Flemish uni every year).
And a final one: not a lot of people here seem to work on machine translation, but if you’re interested and in the neighborhood: UGent will be organizing EAMT next year, June 1-3! It’s a three-day conference on everything MT-related in Ghent. It’s a lot of fun, good food, and interesting talks. If you want to keep updated follow me or @ugentnlp. It’s a great networking opportunity too, as there are always a number of high-quality sponsors such as Microsoft, Unbabel, Crosslang, etc.