dhwajraj/deep-siamese-text-similarity

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1414 stars · 438 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A TensorFlow implementation of a deep siamese LSTM network that learns phrase and sentence similarity using character-level and word-level embeddings. It trains on pairs of texts with a contrastive loss to capture semantic and structural similarity.

Use cases

• measure similarity between two sentences
• match person name variants and abbreviations
• detect duplicate or paraphrased phrases
• train a model to score semantic similarity of text pairs
• learn character-level embeddings for typo-tolerant string matching

When to choose

• you need a reference implementation of siamese LSTMs for text similarity research
• you want to learn pair-based similarity with character or word embeddings on legacy TensorFlow 1.x

When to avoid

• you need production-grade code - the author explicitly marks it as an experimental prototype
• you use modern TensorFlow 2.x or PyTorch - it targets TensorFlow 1.2
• you want a maintained library or pretrained sentence embedding model

Facets

library · maturity abandoned

machine-learning nlp deep-learning machine-learning deep-learning python siamese-network lstm text-similarity word-embeddings character-embeddings tensorflow sentence-pair-scoring natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="dhwajraj/deep-siamese-text-similarity")