[ allennlp.data.dataset_readers.babi ]
class BabiReader(DatasetReader): | def __init__( | self, | keep_sentences: bool = False, | token_indexers: Dict[str, TokenIndexer] = None, | **kwargs | ) -> None
Reads one single task in the bAbI tasks format as formulated in Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks (https://arxiv.org/abs/1502.05698). Since this class handle a single file, if one wants to load multiple tasks together it has to merge them into a single file and use this reader.
Registered as a
DatasetReader with name "babi".
- keep_sentences :
bool, optional (default =
Whether to keep each sentence in the context or to concatenate them. Default is
Falsethat corresponds to concatenation.
- token_indexers :
Dict[str, TokenIndexer], optional (default =
We use this to define the input representation for the text. See
| @overrides | def text_to_instance( | self, | context: List[List[str]], | question: List[str], | answer: str, | supports: List[int] | ) -> Instance