The slides of 2023-24. Slides updated for 2024-25 will be gradually removed.
| Type | Filename  | Size | Date | |
|---|---|---|---|---|
| nlp_slides_part06_nlp_with_transformers.pdf Key-query-value attention,Transformer encoders and decoders. Pre-trained Transformers, fine-tuning, prompting, instruction-tuning, BERT, SMITH, BART, T5, GPT-3, Instruct-GPT, Chat-GPT. Retrieval-augmented generation (RAG), Transformers with tools. Data augmentation for NLP. | 6.11 MB | 1/3/24 | ||
| nlp_slides_part07_speech_recognition.pdf Introduction to automatic speech recognition (ASR). Encoding speech frames with pre-trained Transformers, wav2vec, HuBERT. ASR models: encoder/decoder models, encoder-only models, use of language models. ASR evaluation measures. Optional older material: MFCC vectors, HMM models. | 2.87 MB | 1/3/24 | ||
| nlp_slides_part08_dialogue_systems.pdf Introduction to spoken and written dialog systems. Systems that use rules, information retrieval, automata, grammars, frames, deep learning, pre-trained neural language models. | 1.96 MB | 1/9/24 |
