airalcorn2/Deep-Semantic-Similarity-Model
My Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent Semantic Model (CLSM) described here: http://research.microsoft.com/pubs/226585/cikm2014_cdssm_final.pdf.
This tool helps you evaluate how closely two pieces of text relate to each other, even if they don't share many words. You input pairs of text, and it outputs a score indicating their semantic similarity. This is useful for anyone working with large amounts of text who needs to understand the underlying meaning between queries and documents, like search engine developers or information retrieval specialists.
521 stars. No commits in the last 6 months.
Use this if you need to build or improve a system that matches user queries to relevant documents or finds similar content based on meaning, not just keywords.
Not ideal if you don't have your own extensive, specialized text data to train the model for your specific problem.
Stars
521
Forks
184
Language
Python
License
MIT
Category
Last pushed
Jun 05, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/airalcorn2/Deep-Semantic-Similarity-Model"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
shibing624/similarities
Similarities: a toolkit for similarity calculation and semantic search....
explosion/sense2vec
🦆 Contextually-keyed word vectors
chakki-works/chakin
Simple downloader for pre-trained word vectors
sebischair/Lbl2Vec
Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with...
christiansafka/img2vec
:fire: Use pre-trained models in PyTorch to extract vector embeddings for any image