Teaching a Massive Open Online Course on Natural Language Processing
arXiv:2104.12846 · doi:10.18653/v1/2021.teachingnlp-1.2
Abstract
This paper presents a new Massive Open Online Course on Natural Language Processing, targeted at non-English speaking students. The course lasts 12 weeks; every week consists of lectures, practical sessions, and quiz assignments. Three weeks out of 12 are followed by Kaggle-style coding assignments. Our course intends to serve multiple purposes: (i) familiarize students with the core concepts and methods in NLP, such as language modeling or word or sentence representations, (ii) show that recent advances, including pre-trained Transformer-based models, are built upon these concepts; (iii) introduce architectures for most demanded real-life applications, (iv) develop practical skills to process texts in multiple languages. The course was prepared and recorded during 2020, launched by the end of the year, and in early 2021 has received positive feedback.
arXiv commentTo appear in the Proceedings of the Fifth Workshop on Teaching NLP @ NAACL
References in corpus (9)
- SMOTE: Synthetic Minority Over-sampling Technique
- Distributed Representations of Words and Phrases and their Compositionality
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Distributed Representations of Sentences and Documents
- Probabilistic Latent Semantic Analysis
- Non-Autoregressive Neural Machine Translation
- Q8BERT: Quantized 8Bit BERT
- A Unified MRC Framework for Named Entity Recognition