Natural Language Processing Learning to Reason Over Tables from Less Data In "Understanding tables with intermediate pre-training", published in Findings of EMNLP 2020, we introduce the first pre-training tasks customized for table parsing, enabling models to learn better, faster and from less data.
Natural Language Processing Efficient multi-lingual language model fine-tuning Our latest paper studies multilingual text classification and introduces MultiFiT, a novel method based on ULMFiT. MultiFiT, trained on 100 labeled documents in the target language, outperforms multi-lingual BERT, and the LASER algorithm—even though LASER requires a corpus of parallel texts.
Automatic Differentiation Neural Networks in 100 lines of pure Python Can we build a Deep learning framework in plain Python and Numpy? Can we make it compact, clear and extendable? Let's set out to explore those ideas and see what we can create!
Natural Language Processing Text Classification with TensorFlow Estimators Throughout this post we will explain how to classify text using Estimators, Datasets and Feature Columns, with a scalable high-level API in TensorFlow.