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

Course code : INF312

M35209F/Μ36209P - Text Analytics (MSc Data Science)

INF312  -  Ion Androutsopoulos

Documents
Root directory in_class_demos_2024_25   Files for the in-class demos of 2024-25.
Cancel
First Name Size Date
Lab 1 (N-gram Language Models)
Introduction to the NLTK library. Tokenization and N-gram Language Models (LMs). Cross-entropy and perplexity of LMs. Beam-search decoding.
528.32 KB 4/7/25, 6:12 PM
Lab 2 (Text Classification w/ MLPs)
Introduction to PyTorch. Text classification with MLPs using tf-idf vectors and centroids of pretrained word2vec embeddings. Example with word2vec word embeddings with gensim.
550.68 KB 5/9/25, 9:56 PM
Lab 3 (Text Classification w/ RNNs)
Text classification with RNNs in PyTorch.
378.24 KB 5/21/25, 6:54 PM
Lab 4 (Text Classification w/ CNNs)
Text classification with CNNs in PyTorch.
346.43 KB 6/4/25, 6:10 PM
Lab 5 (Text/Token Classification with Transformers)
Text and token classification with Transformers in PyTorch using HuggingFace🤗. Parameter efficient fine-tuning with LoRA.
53.95 KB 6/10/25, 6:18 PM
Lab 6 (LLMs)
Prompt templates, LangChain Expression Language (LCEL), Chatbots with memory and Agents with tools using LangChain and LangGraph. Zero-shot NER extractions with GPT-4.1. Parameter efficient fine-tuning with LoRA. Faster inference with TGI. Serve LLM apps with Gradio.
104.18 KB 6/19/25, 2:29 PM