mavalliani / Semantic-Similarity-of-Sentences

Methods used: Cosine Similarity with Glove, Smooth Inverse Frequency, Word Movers Difference, Sentence Embedding Models (Infersent and Google Sentence Encoder), ESIM with pre-trained FastText embedding. Best performing method on Quora Question pair dataset was an Ensemble method with 0.27 log-loss.
17Updated 4 years ago

Alternatives and similar repositories for Semantic-Similarity-of-Sentences:

Users that are interested in Semantic-Similarity-of-Sentences are comparing it to the libraries listed below