Package de.uni_mannheim.informatik.dws.melt.matching_ml.python.nlptransformers
package de.uni_mannheim.informatik.dws.melt.matching_ml.python.nlptransformers
-
ClassDescriptionAn enum which describes entities on how to optimize the batch size.This filter asks a LLM which entity of the source fits best to an entity of the target.This filter asks a LLM if a given correspondence is correct or not.This filter asks the LLM given a source entity which is the best target entity (out of the ones in the alignment).This matcher uses the Sentence Transformers library to build an embedding space for each resource given a textual representation of it.Enum which lists all possible types of loss for training sentence transformers.This matcher uses the Sentence Transformers library to build an embedding space for each resource given a textual representation of it.This class represents the arguments for the transformers library.This is a base class for all Transformers.This is a base class for all Transformers fine tuners.This filter extracts the corresponding text for a resource (with the specified and customizable extractor) given all correspondences in the input alignment.This class is used to fine-tune a transformer model based on a generated dataset.This class represents the search space for hyper parameters.The transformers library may not free all memory from GPU.The enum which represents the possible measure for evaluating a model during hyperparameter search.