This interface allows you to compare the similarity of sequential sentences within a particular LSA space, with word2vec word embeddings, or using the BERT language model. Each sentence is compared to next sentence. The program will automatically parse the input into sentences based on the use of end of sentence punctuation -- you do not have to separate sentences on different lines.
To compute the similarity of multiple sentences, enter your text in the input box below. Use normal punctuation to separate each sentence. Then press the 'Submit Texts' button. The system will compute a cosine similarity score for each submitted text compared to all submitted texts.