https://github.com/joaquimgomez/bachelorsthesis-textsimilaritymeasures

Code and models used in my Bachelor’s Degree Thesis about large text similarity measures are here. The similarities have been combined with machine learning based embeddings. This repository also contains raw results obtained from tasks/experiments.

bert cosine-similarity doc2vec elmo embeddings fasttext glove normalized-relative-compression soft-cosine-similarity text-similarity thesis-project word-mover-distance word2vec

Last synced: 07 Aug 2025