Solving Natural Language problems with scarce data by Álvaro Barbero
In this talk Álvaro will introduce the concept of language models, and review some of the state of the art approaches to building such models (BERT, GPT-2 and XLNet), delving into the network architecture and training strategies used in them. Then he will move on to show how these pre-trained language models can be fine-tuned to small datasets to produce high quality results in downstream NLP tasks, by making use of the open-source PyTorch-Transformers library (https://github.com/huggingface/pytorc.... This library is built on top of the PyTorch deep learning framework, and allows loading pre-trained language models and fine-tuning them easily. This talk will be focused on the theoretical grounds of these methods and on his practical experience in applying them.
#BIGTH19 #DataScience #DeepLearning
Session presented at Big Things Conference 2019 by Álvaro Barbero, Chief Data Scientist at IIC.
20th November 2019
Kinépolis, Madrid
Do you want to know more? https://www.bigthingsconference.com/