allennlp.models.semantic_parsing¶
-
class
allennlp.models.semantic_parsing.text2sql_parser.Text2SqlParser(vocab: allennlp.data.vocabulary.Vocabulary, utterance_embedder: allennlp.modules.text_field_embedders.text_field_embedder.TextFieldEmbedder, action_embedding_dim: int, encoder: allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder, decoder_beam_search: allennlp.state_machines.beam_search.BeamSearch, max_decoding_steps: int, input_attention: allennlp.modules.attention.attention.Attention, add_action_bias: bool = True, dropout: float = 0.0, 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- Parameters
- vocab
Vocabulary - utterance_embedder
TextFieldEmbedder Embedder for utterances.
- action_embedding_dim
int Dimension to use for action embeddings.
- encoder
Seq2SeqEncoder The encoder to use for the input utterance.
- decoder_beam_search
BeamSearch Beam search used to retrieve best sequences after training.
- max_decoding_steps
int When we’re decoding with a beam search, what’s the maximum number of steps we should take? This only applies at evaluation time, not during training.
- input_attention: ``Attention``
We compute an attention over the input utterance at each step of the decoder, using the decoder hidden state as the query. Passed to the transition function.
- add_action_bias
bool, optional (default=True) If
True, we will learn a bias weight for each action that gets used when predicting that action, in addition to its embedding.- dropout
float, optional (default=0) If greater than 0, we will apply dropout with this probability after all encoders (pytorch LSTMs do not apply dropout to their last layer).
- vocab
-
decode(self, output_dict: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor][source]¶ This method overrides
Model.decode, which gets called afterModel.forward, at test time, to finalize predictions. This is (confusingly) a separate notion from the “decoder” in “encoder/decoder”, where that decoder logic lives inTransitionFunction.This method trims the output predictions to the first end symbol, replaces indices with corresponding tokens, and adds a field called
predicted_actionsto theoutput_dict.
-
forward(self, tokens: Dict[str, torch.LongTensor], valid_actions: List[List[allennlp.data.fields.production_rule_field.ProductionRule]], action_sequence: torch.LongTensor = None) → Dict[str, torch.Tensor][source]¶ We set up the initial state for the decoder, and pass that state off to either a DecoderTrainer, if we’re training, or a BeamSearch for inference, if we’re not.
- Parameters
- tokensDict[str, torch.LongTensor]
The output of
TextField.as_array()applied on the tokensTextField. This will be passed through aTextFieldEmbedderand then through an encoder.- valid_actions
List[List[ProductionRule]] A list of all possible actions for each
Worldin the batch, indexed into aProductionRuleusing aProductionRuleField. We will embed all of these and use the embeddings to determine which action to take at each timestep in the decoder.- action_sequencetorch.Tensor, optional (default=None)
The action sequence for the correct action sequence, where each action is an index into the list of possible actions. This tensor has shape
(batch_size, sequence_length, 1). We remove the trailing dimension.
-
get_metrics(self, reset: bool = False) → Dict[str, float][source]¶ We track four metrics here:
1. exact_match, which is the percentage of the time that our best output action sequence matches the SQL query exactly.
2. denotation_acc, which is the percentage of examples where we get the correct denotation. This is the typical “accuracy” metric, and it is what you should usually report in an experimental result. You need to be careful, though, that you’re computing this on the full data, and not just the subset that can be parsed. (make sure you pass “keep_if_unparseable=True” to the dataset reader, which we do for validation data, but not training data).
3. valid_sql_query, which is the percentage of time that decoding actually produces a valid SQL query. We might not produce a valid SQL query if the decoder gets into a repetitive loop, or we’re trying to produce a super long SQL query and run out of time steps, or something.
4. action_similarity, which is how similar the action sequence predicted is to the actual action sequence. This is basically a soft measure of exact_match.