NLP

A Journey through TF-IDF, vector space, and text classification

Before reaching for an LLM API on every classification problem, it's worth knowing what a decades-old baseline can already do with the labeled data you have — and exactly how much more data buys you.

From unstructured text to structured Knowledge Graphs

How simple statistics reveal the visual fingerprints of 20 languages

Lessons learned deploying a domain-specific NER model

Effortless extraction of data and tables from PDF documents

POS tagging, dependency parser and named entity recognition

Learn about tokenization, lemmatization and the core operations

How machines make sense of sentence structure: Combinatory Categorial Grammar

Implementing one of the earliest neural image caption generator models with PyTorch.