Course : M35209F/Μ36209P - Text Analytics (MSc Data Science)

Course code : INF312

INF312  -  Ion Androutsopoulos

Documents
Root directory ta_slides_2024_25   The slides of 2024-25. Files updated for 2025-26 may be gradually removed.
First Name Size Date
Quick background on Convolutional Neural Networks (CNNs) in Computer Vision. Text processing with CNNs. Image to text generation with CNN encoders and RNN decoders.
2.34 MB 12/30/24, 12:21 PM
Key-query-value attention, multi-head attention, Transformer encoders and decoders. Pre-trained Transformers and Large Language Models (LLMs), BERT, SMITH, BART, T5, GPT-3, InstructGPT, ChatGPT, and open-source alternatives, fine-tuning them, prompting them. Parameter efficient training, LoRA. Retrieval-augmented generation (RAG), LLMs with tools. Data augmentation for NLP. Adding vision to LLMs, LLaVA, InstructBLIP.
4.93 MB 12/30/24, 12:21 PM
Introduction to automatic speech recognition (ASR). Encoding speech frames with pre-trained Transformers, wav2vec, HuBERT. ASR models: encoder/decoder models, encoder-only models. ASR evaluation measures. Optional older material: MFCC vectors, HMM models.
2.82 MB 12/30/24, 12:22 PM