Package de.uni_mannheim.informatik.dws.melt.matching_ml.python.nlptransformers

Class LLMChooseGivenEntityFilter

java.lang.Object
eu.sealsproject.platform.res.tool.impl.AbstractPlugin
de.uni_mannheim.informatik.dws.melt.matching_base.MatcherURL
de.uni_mannheim.informatik.dws.melt.matching_base.MatcherFile
de.uni_mannheim.informatik.dws.melt.matching_jena.MatcherYAAA
de.uni_mannheim.informatik.dws.melt.matching_jena.MatcherYAAAJena
de.uni_mannheim.informatik.dws.melt.matching_ml.python.nlptransformers.TransformersBase
de.uni_mannheim.informatik.dws.melt.matching_ml.python.nlptransformers.LLMBase
de.uni_mannheim.informatik.dws.melt.matching_ml.python.nlptransformers.LLMChooseGivenEntityFilter
All Implemented Interfaces:
Filter, IMatcher<org.apache.jena.ontology.OntModel,Alignment,Properties>, eu.sealsproject.platform.res.domain.omt.IOntologyMatchingToolBridge, eu.sealsproject.platform.res.tool.api.IPlugin, eu.sealsproject.platform.res.tool.api.IToolBridge
public class LLMChooseGivenEntityFilter extends LLMBase implements Filter
This filter asks the LLM given a source entity which is the best target entity (out of the ones in the alignment). Afterwards the same is done in the reversed direction.

  • Field Details

    • NEWLINE

      private static final String NEWLINE

    • LOGGER

      private static final org.slf4j.Logger LOGGER

    • useNumbers

      protected boolean useNumbers

    • BINARY_ADDITIONAL_CONFIDENCE_KEY

      public static final String BINARY_ADDITIONAL_CONFIDENCE_KEY

  • Constructor Details

    • LLMChooseGivenEntityFilter

      public LLMChooseGivenEntityFilter(TextExtractorMap extractor, String modelName, String promt)
      Constructor with all required parameters and default values for optional parameters (can be changed by setters). It uses the systems default tmp dir to store the files with texts generated from the knowledge graphs. Pytorch is used instead of tensorflow and all visible GPUs are used for prediction.
      Parameters:
      extractor - the extractor to select which text for each resource should be used.
      modelName - the model name which can be a model id (a hosted model on huggingface.co) or a path to a directory containing a model and tokenizer ( see first parameter pretrained_model_name_or_path of the from_pretrained function in huggingface library). In case of a path, it should be absolute. The path can be generated by e.g. FileUtil.getCanonicalPathIfPossible(java.io.File)
      promt - The promt to use for the LLM. Use text {candidates} to insert the text representation of all candidates with alphabetical enumerations.

    • LLMChooseGivenEntityFilter

      public LLMChooseGivenEntityFilter(TextExtractor extractor, String modelName, String promt)
      Constructor with all required parameters and default values for optional parameters (can be changed by setters). It uses the systems default tmp dir to store the files with texts generated from the knowledge graphs. Pytorch is used instead of tensorflow and all visible GPUs are used for prediction.
      Parameters:
      extractor - the extractor to select which text for each resource should be used.
      modelName - the model name which can be a model id (a hosted model on huggingface.co) or a path to a directory containing a model and tokenizer ( see first parameter pretrained_model_name_or_path of the from_pretrained function in huggingface library). In case of a path, it should be absolute. The path can be generated by e.g. FileUtil.getCanonicalPathIfPossible(java.io.File)
      promt - The promt to use for the LLM. Use {left} and {right} to insert the text representation of the left and right concept.

  • Method Details

    • match

      public Alignment match(org.apache.jena.ontology.OntModel source, org.apache.jena.ontology.OntModel target, Alignment inputAlignment, Properties properties) throws Exception
      Description copied from class: MatcherYAAAJena
      Aligns two ontologies specified via a Jena OntModel, with an input alignment as Alignment object, and returns the mapping of the resulting alignment. Note: This method might be called multiple times in a row when using the evaluation framework. Make sure to return a mapping which is specific to the given inputs.
      Specified by:
      match in interface IMatcher<org.apache.jena.ontology.OntModel,Alignment,Properties>
      Specified by:
      match in class MatcherYAAAJena
      Parameters:
      source - This OntModel represents the source ontology.
      target - This OntModel represents the target ontology.
      inputAlignment - This mapping represents the input alignment.
      properties - Additional properties.
      Returns:
      The resulting alignment of the matching process.
      Throws:
      Exception - Any exception which occurs during matching.

    • getEnumerationLabel

      private String getEnumerationLabel(int i)

    • getList

      private List<Correspondence> getList(Iterable<Correspondence> a)

    • generateWordsToDetect

      private List<Set<String>> generateWordsToDetect(int maxNumberOfCandidates)

    • getOneTextualRepresentation

      protected String getOneTextualRepresentation(org.apache.jena.rdf.model.Resource r, Map<org.apache.jena.rdf.model.Resource,String> cache)