Skip to content

transformer_qa

allennlp_models.rc.predictors.transformer_qa

[SOURCE]

TransformerQAPredictor#

@Predictor.register("transformer_qa")
class TransformerQAPredictor(Predictor):
 | def __init__(
 |     self,
 |     model: Model,
 |     dataset_reader: DatasetReader
 | ) -> None

Predictor for the TransformerQA model, and any other model that takes a question and passage as input.

predict#

class TransformerQAPredictor(Predictor):
 | ...
 | def predict(self, question: str, passage: str) -> JsonDict

Make a machine comprehension prediction on the supplied input. See https://rajpurkar.github.io/SQuAD-explorer/ for more information about the machine comprehension task.

Parameters

  • question : str
    A question about the content in the supplied paragraph.

  • passage : str
    A paragraph of information relevant to the question.

Returns

  • JsonDict
    A dictionary that represents the prediction made by the system. The answer string will be under the "best_span_str" key.

predict_json#

class TransformerQAPredictor(Predictor):
 | ...
 | def predict_json(self, inputs: JsonDict) -> JsonDict

predictions_to_labeled_instances#

class TransformerQAPredictor(Predictor):
 | ...
 | @overrides
 | def predictions_to_labeled_instances(
 |     self,
 |     instance: Instance,
 |     outputs: Dict[str, numpy.ndarray]
 | ) -> List[Instance]

predict_batch_json#

class TransformerQAPredictor(Predictor):
 | ...
 | @overrides
 | def predict_batch_json(self, inputs: List[JsonDict]) -> List[JsonDict]

predict_batch_instance#

class TransformerQAPredictor(Predictor):
 | ...
 | @overrides
 | def predict_batch_instance(
 |     self,
 |     instances: List[Instance]
 | ) -> List[JsonDict]