class allennlp.models.esim.ESIM(vocab:, text_field_embedder: allennlp.modules.text_field_embedders.text_field_embedder.TextFieldEmbedder, encoder: allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder, similarity_function: allennlp.modules.similarity_functions.similarity_function.SimilarityFunction, projection_feedforward: allennlp.modules.feedforward.FeedForward, inference_encoder: allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder, output_feedforward: allennlp.modules.feedforward.FeedForward, output_logit: allennlp.modules.feedforward.FeedForward, dropout: float = 0.5, initializer: allennlp.nn.initializers.InitializerApplicator = <allennlp.nn.initializers.InitializerApplicator object>, regularizer: Optional[allennlp.nn.regularizers.regularizer_applicator.RegularizerApplicator] = None)[source]

Bases: allennlp.models.model.Model

This Model implements the ESIM sequence model described in “Enhanced LSTM for Natural Language Inference” by Chen et al., 2017.


Used to embed the premise and hypothesis TextFields we get as input to the model.


Used to encode the premise and hypothesis.


This is the similarity function used when computing the similarity matrix between encoded words in the premise and words in the hypothesis.


The feedforward network used to project down the encoded and enhanced premise and hypothesis.


Used to encode the projected premise and hypothesis for prediction.


Used to prepare the concatenated premise and hypothesis for prediction.


This feedforward network computes the output logits.

dropoutfloat, optional (default=0.5)

Dropout percentage to use.

initializerInitializerApplicator, optional (default=``InitializerApplicator()``)

Used to initialize the model parameters.

regularizerRegularizerApplicator, optional (default=``None``)

If provided, will be used to calculate the regularization penalty during training.

forward(self, premise: Dict[str, torch.LongTensor], hypothesis: Dict[str, torch.LongTensor], label: torch.IntTensor = None, metadata: List[Dict[str, Any]] = None) → Dict[str, torch.Tensor][source]
premiseDict[str, torch.LongTensor]

From a TextField

hypothesisDict[str, torch.LongTensor]

From a TextField

labeltorch.IntTensor, optional (default = None)

From a LabelField

metadataList[Dict[str, Any]], optional, (default = None)

Metadata containing the original tokenization of the premise and hypothesis with ‘premise_tokens’ and ‘hypothesis_tokens’ keys respectively.

An output dictionary consisting of:

A tensor of shape (batch_size, num_labels) representing unnormalised log probabilities of the entailment label.


A tensor of shape (batch_size, num_labels) representing probabilities of the entailment label.

losstorch.FloatTensor, optional

A scalar loss to be optimised.

get_metrics(self, reset: bool = False) → Dict[str, float][source]

Returns a dictionary of metrics. This method will be called by in order to compute and use model metrics for early stopping and model serialization. We return an empty dictionary here rather than raising as it is not required to implement metrics for a new model. A boolean reset parameter is passed, as frequently a metric accumulator will have some state which should be reset between epochs. This is also compatible with Metrics should be populated during the call to ``forward`, with the Metric handling the accumulation of the metric until this method is called.