TokenSearcherRelationExtraction

Relation extraction task

This task uses TokenSearcherPredictor by default. For more details, see:

TokenSearcherPredictor

Subclass of Task.

Module: implementation.tasks

Methods and properties

Main methods and properties

---

__init__

Arguments:

• predictor (Predictor[Any, Any], optional): Predictor that will be used in task. If equals to None, default TokenSearcherPredictor will be used. Defaults to None.

• preprocess (Optional[Component], optional): Component executed before predictor.

  If equals to None, default component will be used. Defaults to None. Default component: TokenSearcherRelationExtractionPreprocessor

• postprocess (Optional[Component], optional): Component executed after predictor.

  If equals to None, default component will be used. Defaults to None. Default component: TokenSearcherRelationExtractionPostprocessor

• input_class (Type[Input], optional): Class for input validation. Defaults to RelationExtractionInput.

• output_class (Type[Output], optional): Class for output validation. Defaults to RelationExtractionOutput.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

---

---

TokenSearcherRelationExtractionPreprocessor

Create prompt with providied text. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "text" (str): Text to process;

  • "relations" (List[Relation]): Relations parameters;

  • "entities" (List[ClassifiedEntity]): Entities to use;

Returns:

• Dict[str, Any]: Expected keys:

  • "source_entities" (List[ClassifiedEntity]): Source entities to use;

  • "relations_labels" (List[str]): Corresponding relations labels;

  • "inputs" (List[str]): Model inputs;

  • "prompt_lengths" (List[int]): Prompt lenghts. Used by postprocessor;

---

---

---

TokenSearcherRelationExtractionPostprocessor

Format output. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

__init__

Arguments:

• threshold (float): Relations threshold score. Defaults to 0.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "text" (str): Processed text;

  • "output" (List[List[Dict[str, Any]]]): Model output;

  • "relations" (List[Relation]): Relations parameters;

  • "source_entities" (List[ClassifiedEntity]): Used source entities;

  • "relations_labels" (List[str]): Corresponding relations labels;

  • "entities" (List[ClassifiedEntity]): Entities to use;

  • "prompt_lengths" (List[int]): Prompt lenghts;

Returns:

• Dict[str, Any]: Expected keys:

  • "output" (List[Triplets]): Extracted relations;

---

---