NLP Methods Explorer

Browse classical and modern NLP methods, then open interactive demos to understand how each method works step by step.

Search and filter

Narrow the catalog by method name, category, difficulty, or demo status.

Method Catalog

Showing 12 of 12 methods.

Interactive Demo Available

4-Gram Language Model

Statistical Language ModelBeginner

Predicts the next word from the previous three words.

What you can inspect

  • token counts
  • vocabulary size
  • n-gram frequency
  • smoothing
  • perplexity
  • generated text trace
Coming Soon

Bigram Language Model

Statistical Language ModelBeginner

Predicts the next word using only one previous word.

What you can inspect

  • bigram counts
  • transition probability
  • generated sequence
Coming Soon

Trigram Language Model

Statistical Language ModelBeginner

Predicts the next word using two previous words.

What you can inspect

  • trigram counts
  • conditional probability
  • generation trace
Coming Soon

Markov Chain Text Generator

Statistical Language ModelBeginner

Generates text by moving from one state to another based on learned probabilities.

What you can inspect

  • state transition table
  • probability graph
  • generated path
Coming Soon

TF-IDF

Vector Space ModelBeginner

Measures how important a word is inside a document collection.

What you can inspect

  • term frequency
  • inverse document frequency
  • document score table
Coming Soon

Word2Vec

Embedding ModelIntermediate

Learns word meaning by placing similar words close together in vector space.

What you can inspect

  • word vectors
  • nearest words
  • similarity score
Coming Soon

RNN Language Model

Neural Language ModelIntermediate

Processes text step by step using hidden states.

What you can inspect

  • hidden state flow
  • sequence prediction
  • training loss
Coming Soon

LSTM Language Model

Neural Language ModelIntermediate

Improves RNNs by remembering useful information over longer sequences.

What you can inspect

  • memory cell
  • gates
  • sequence prediction
Coming Soon

Seq2Seq with Attention

Neural Language ModelIntermediate

Maps one sequence to another while using attention to focus on the most relevant input tokens.

What you can inspect

  • encoder states
  • attention alignment
  • decoded sequence
Coming Soon

Transformer Language Model

Transformer ModelAdvanced

Uses attention to learn relationships between words across longer context.

What you can inspect

  • attention weights
  • token embeddings
  • generated output
Coming Soon

BERT

Transformer ModelAdvanced

Learns bidirectional context for language understanding tasks such as classification and question answering.

What you can inspect

  • masked tokens
  • context embeddings
  • classification logits
Coming Soon

RAG

Retrieval-Based ModelAdvanced

Combines document search with text generation to create grounded answers.

What you can inspect

  • retrieved documents
  • context chunks
  • generated answer

Method Comparison Summary

A concise view of where each method is useful and what to watch for.

MethodMain IdeaStrengthLimitationBest For
4-GramPredict from the previous three words.Easy to inspect and explain.Struggles with unseen contexts.Learning statistical text generation.
TF-IDFScore words by document importance.Fast and transparent.Does not understand word meaning.Search and keyword analysis.
Word2VecRepresent words as vectors.Captures similarity between words.Needs enough training data.Semantic comparison.
TransformerUse attention across context.Handles long-range relationships.More complex and resource-heavy.Modern language modeling.
RAGRetrieve documents before generation.Can ground answers in sources.Depends on retrieval quality.Question answering over documents.

Recommended Learning Path

Start with simple statistical models before moving to neural and transformer-based methods.

  1. 1Bigram
  2. 2Trigram
  3. 34-Gram
  4. 4Markov Chain
  5. 5TF-IDF
  6. 6Word2Vec
  7. 7RNN
  8. 8LSTM
  9. 9Transformer
  10. 10RAG