| Jan 22 |
Introduction |
|
NLP (circa 2001) |
| Jan 24 |
" |
|
|
| |
Warming up! |
|
|
| |
Text classification, data basics, and the perceptron |
|
|
| Jan 29 |
" |
|
|
| |
Neural networks basics |
|
Back-prop, Deep Averaging Networks, Gradient Checks (briefly), Gradient Checks (in details) |
| Jan 31 |
" |
|
|
| Feb 05 |
Learning from raw data |
|
|
| |
Word embeddings |
|
w2v explained, Levy2014, word2vec, word2vec phrases, Hill2016, Turney2010 |
| Feb 07 |
" |
|
|
| Feb 12 |
" |
|
|
| |
Language modeling |
|
Collins: LM, Smoothing, More about smoothing |
| Feb 14 |
" |
|
|
| Feb 19 |
Tokenization |
|
Mielke2021, BPE notebook, HF summary |
| |
Neural LMs and Transformers |
|
Annotated Transformer, Illustrated Transformer, Vaswani2017 |
| Feb 21 |
" |
|
|
| Feb 26 |
No class ⛷️ |
|
|
| Feb 28 |
Neural LMs and Transformers |
|
|
| Mar 04 |
" |
|
|
| |
Decoding LMs |
|
|
| |
Scaling up to LLMs |
|
|
| Mar 06 |
" |
|
|
| Mar 11 |
Masked LMs |
|
|
| |
Raw data recap |
|
|
| |
Learning from annotated data |
|
|
| |
Prototypical NLP tasks |
|
|
| Mar 13 |
" |
|
|
| Mar 18 |
" |
|
|
| Mar 20 |
" |
|
|
| Mar 25 |
" |
|
|
| Mar 27 |
" |
|
|
| Apr 01 |
No class ⛱️ |
|
|
| Apr 03 |
No class 🏖️ |
|
|
| Apr 08 |
" |
|
|
| |
Aligning LLMs |
|
|
| Apr 10 |
" |
|
|
| Apr 15 |
" |
|
|
| Apr 17 |
Guest lecture: Orhan Firat (Google) – LLMs at Google |
|
|
| Apr 22 |
Aligning LLMs |
|
|
| Apr 24 |
Guest lecture: Joel Tetreault (Dataminr) – History of NLP |
|
|
| Apr 29 |
Working with LLMs: Prompting |
|
|
| May 01 |
" |
|
|
| |
Encoder-decoder Pre-training |
|
|
| May 06 |
Recurrent neural networks |
|
|