Browser-based NLP tools for preprocessing, sentiment, retrieval, question answering, translation, summarisation, speech-to-text, entities, POS tagging, and language generation.
Learning area
These pages are grouped as a learning collection. More lecture notes, examples, and practical tools can be added without changing the page structure.
Available resources
Available resources
This category combines current MuhammadLab pages that match the topic. More lecture guides and interactive tools can be added here as the lab grows.
Train a small n-gram language model, type a context, predict likely next words, and inspect probability, smoothing, and generation calculations.
Paste or upload text and inspect tokenization, stop word removal, stemming, lemmatization, n-grams, entities, POS signals, and text statistics.
Build a mini search engine in the browser: edit documents, enter a query, rank results with TF-IDF and cosine similarity, and inspect the retrieval calculations.
Learn TF-IDF with editable example documents, term scoring, query ranking, cosine similarity, and top-keyword tables.
Understand Transformers with self-attention intuition, why they scale, and common model variants (encoder/decoder).
Learn what BERT is, masked language modeling, embeddings, and typical NLP uses.
Check your text for style, clarity, passive voice, weasel words, and sensitive language — a free, browser-based alternative to Grammarly powered by open NLP tools.
Explore simple language generation with a browser-based n-gram model, inspect next-token probabilities, and generate short continuations from custom text.
Identify people, places, organisations, dates, and other entity-like signals from text using a browser-based NLP workflow.
Paste text and inspect how a browser-based NLP pipeline highlights noun phrases, verbs, adjectives, and token-level language structure for classroom analysis.
Use your microphone to turn short spoken phrases into text in the browser and inspect live transcription output for teaching speech-to-text workflows.
Learn how Word2Vec creates vector embeddings and why semantics emerge from co-occurrence.
Paste a passage, ask a question, and see how a transformer reading-comprehension model selects an answer span from the provided context.
Translate short passages between supported languages using a browser transformer model, and learn how encoder-decoder translation works.
Paste a paragraph and see how a transformer summarisation model compresses the main ideas into a shorter summary, with clear metrics.
Type text and see how a transformer model predicts positive, negative, or neutral/uncertain sentiment with confidence scores.
Learn Bayes’ rule, conditional independence, and why Naive Bayes is strong for text.