facebookresearch/InferSent

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

2280 stars · 463 forks observed · 2026-08-28

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

InferSent is a sentence embedding method from Facebook AI Research that produces semantic representations for English sentences using a model trained on natural language inference data. It provides pre-trained encoders (GloVe and fastText versions) plus a demo notebook for encoding sentences.

Use cases

• generate sentence embeddings for English text
• encode sentences into semantic vectors for downstream tasks
• compute semantic similarity between sentences
• use pretrained NLI-trained sentence encoder in PyTorch
• get fixed-size vector representations of sentences for classification or retrieval

When to choose

• you need classic pre-transformer sentence embeddings for English
• you want a simple PyTorch encoder with pretrained GloVe or fastText word vectors
• you are reproducing research from the InferSent paper or SentEval benchmarks

When to avoid

• you need actively maintained software or support for languages other than English
• you want state-of-the-art contextual embeddings from transformer models
• you need multilingual sentence embeddings

Facets

library · maturity abandoned

nlp machine-learning machine-learning deep-learning python sentence-embeddings pytorch pretrained-models natural-language-inference research natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookresearch/InferSent")