ClassBatchHardSoftMarginTripletLoss BatchHardSoftMarginTripletLoss takes a batch with (label, sentence) pairs and computes the loss for all possible, valid triplets, i.e., ancho
sentence_transformers/losses/BatchHardSoftMarginTripletLoss.py:7
ClassContrastiveTensionLoss This loss expects as input a batch consisting of multiple mini-batches of sentence pairs (a_1, p_1), (a_2, p_2)..., (a_{K+1}, p_{K+1})
sentence_transformers/losses/ContrastiveTensionLoss.py:12
ClassMarginMSELoss Compute the MSE loss between the |sim(Query, Pos) - sim(Query, Neg)| and |gold_sim(Q, Pos) - gold_sim(Query, Neg)|. By default, sim() is the
sentence_transformers/losses/MarginMSELoss.py:5
ClassMultipleNegativesRankingLoss This loss expects as input a batch consisting of sentence pairs (a_1, p_1), (a_2, p_2)..., (a_n, p_n) where we assume that (a_i, p_i)
sentence_transformers/losses/MultipleNegativesRankingLoss.py:7
ClassTranslationEvaluator Given two sets of sentences in different languages, e.g. (en_1, en_2, en_3...) and (fr_1, fr_2, fr_3, ...), and assuming that fr_i is the tra
sentence_transformers/evaluation/TranslationEvaluator.py:14