Python allennlp.training.metrics.SquadEmAndF1() Examples
The following are 7
code examples of allennlp.training.metrics.SquadEmAndF1().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
allennlp.training.metrics
, or try the search function
.
.
Example #1
| Source File: bidaf_ensemble.py From magnitude with MIT License | 5 votes |
|
def __init__(self, submodels ) :
super(BidafEnsemble, self).__init__(submodels)
self._squad_metrics = SquadEmAndF1()
#overrides
Example #2
| Source File: slqa_h.py From SLQA with Apache License 2.0 | 5 votes |
|
def __init__(self, vocab: Vocabulary,
text_field_embedder: TextFieldEmbedder,
phrase_layer: Seq2SeqEncoder,
projected_layer: Seq2SeqEncoder,
flow_layer: Seq2SeqEncoder,
contextual_passage: Seq2SeqEncoder,
contextual_question: Seq2SeqEncoder,
dropout: float = 0.2,
regularizer: Optional[RegularizerApplicator] = None,
initializer: InitializerApplicator = InitializerApplicator(),
):
super(MultiGranularityHierarchicalAttentionFusionNetworks, self).__init__(vocab, regularizer)
self._text_field_embedder = text_field_embedder
self._phrase_layer = phrase_layer
self._encoding_dim = self._phrase_layer.get_output_dim()
self.projected_layer = torch.nn.Linear(self._encoding_dim + 1024, self._encoding_dim)
self.fuse = FusionLayer(self._encoding_dim)
self.projected_lstm = projected_layer
self.flow = flow_layer
self.contextual_layer_p = contextual_passage
self.contextual_layer_q = contextual_question
self.linear_self_align = torch.nn.Linear(self._encoding_dim, 1)
self.bilinear_layer_s = BilinearSeqAtt(self._encoding_dim, self._encoding_dim)
self.bilinear_layer_e = BilinearSeqAtt(self._encoding_dim, self._encoding_dim)
self.yesno_predictor = torch.nn.Linear(self._encoding_dim, 3)
self.relu = torch.nn.ReLU()
self._max_span_length = 30
self._span_start_accuracy = CategoricalAccuracy()
self._span_end_accuracy = CategoricalAccuracy()
self._span_accuracy = BooleanAccuracy()
self._squad_metrics = SquadEmAndF1()
self._span_yesno_accuracy = CategoricalAccuracy()
self._official_f1 = Average()
self._variational_dropout = InputVariationalDropout(dropout)
self._loss = torch.nn.CrossEntropyLoss()
initializer(self)
Example #3
| Source File: rnet.py From R-net with MIT License | 5 votes |
|
def __init__(self,
vocab: Vocabulary,
text_field_embedder: TextFieldEmbedder,
question_encoder: Seq2SeqEncoder,
passage_encoder: Seq2SeqEncoder,
pair_encoder: AttentionEncoder,
self_encoder: AttentionEncoder,
output_layer: QAOutputLayer,
initializer: InitializerApplicator = InitializerApplicator(),
regularizer: Optional[RegularizerApplicator] = None,
share_encoder: bool = False):
super().__init__(vocab, regularizer)
self.text_field_embedder = text_field_embedder
self.question_encoder = question_encoder
self.passage_encoder = passage_encoder
self.pair_encoder = pair_encoder
self.self_encoder = self_encoder
self.output_layer = output_layer
self._span_start_accuracy = CategoricalAccuracy()
self._span_end_accuracy = CategoricalAccuracy()
self._span_accuracy = BooleanAccuracy()
self._squad_metrics = SquadEmAndF1()
self.share_encoder = share_encoder
self.loss = torch.nn.CrossEntropyLoss()
initializer(self)
Example #4
| Source File: bidaf.py From magnitude with MIT License | 4 votes |
|
def __init__(self, vocab ,
text_field_embedder ,
num_highway_layers ,
phrase_layer ,
similarity_function ,
modeling_layer ,
span_end_encoder ,
dropout = 0.2,
mask_lstms = True,
initializer = InitializerApplicator(),
regularizer = None) :
super(BidirectionalAttentionFlow, self).__init__(vocab, regularizer)
self._text_field_embedder = text_field_embedder
self._highway_layer = TimeDistributed(Highway(text_field_embedder.get_output_dim(),
num_highway_layers))
self._phrase_layer = phrase_layer
self._matrix_attention = LegacyMatrixAttention(similarity_function)
self._modeling_layer = modeling_layer
self._span_end_encoder = span_end_encoder
encoding_dim = phrase_layer.get_output_dim()
modeling_dim = modeling_layer.get_output_dim()
span_start_input_dim = encoding_dim * 4 + modeling_dim
self._span_start_predictor = TimeDistributed(torch.nn.Linear(span_start_input_dim, 1))
span_end_encoding_dim = span_end_encoder.get_output_dim()
span_end_input_dim = encoding_dim * 4 + span_end_encoding_dim
self._span_end_predictor = TimeDistributed(torch.nn.Linear(span_end_input_dim, 1))
# Bidaf has lots of layer dimensions which need to match up - these aren't necessarily
# obvious from the configuration files, so we check here.
check_dimensions_match(modeling_layer.get_input_dim(), 4 * encoding_dim,
u"modeling layer input dim", u"4 * encoding dim")
check_dimensions_match(text_field_embedder.get_output_dim(), phrase_layer.get_input_dim(),
u"text field embedder output dim", u"phrase layer input dim")
check_dimensions_match(span_end_encoder.get_input_dim(), 4 * encoding_dim + 3 * modeling_dim,
u"span end encoder input dim", u"4 * encoding dim + 3 * modeling dim")
self._span_start_accuracy = CategoricalAccuracy()
self._span_end_accuracy = CategoricalAccuracy()
self._span_accuracy = BooleanAccuracy()
self._squad_metrics = SquadEmAndF1()
if dropout > 0:
self._dropout = torch.nn.Dropout(p=dropout)
else:
self._dropout = lambda x: x
self._mask_lstms = mask_lstms
initializer(self)
Example #5
| Source File: bidaf_pair2vec.py From pair2vec with Apache License 2.0 | 4 votes |
|
def __init__(self, vocab: Vocabulary,
text_field_embedder: TextFieldEmbedder,
phrase_layer: Seq2SeqEncoder,
residual_encoder: Seq2SeqEncoder,
span_start_encoder: Seq2SeqEncoder,
span_end_encoder: Seq2SeqEncoder,
initializer: InitializerApplicator,
dropout: float = 0.2,
pair2vec_dropout: float = 0.15,
max_span_length: int = 30,
pair2vec_model_file: str = None,
pair2vec_config_file: str = None
) -> None:
super().__init__(vocab)
self._max_span_length = max_span_length
self._text_field_embedder = text_field_embedder
self._phrase_layer = phrase_layer
self._encoding_dim = phrase_layer.get_output_dim()
self.pair2vec = pair2vec_util.get_pair2vec(pair2vec_config_file, pair2vec_model_file)
self._pair2vec_dropout = torch.nn.Dropout(pair2vec_dropout)
self._matrix_attention = LinearMatrixAttention(self._encoding_dim, self._encoding_dim, 'x,y,x*y')
# atten_dim = self._encoding_dim * 4 + 600 if ablation_type == 'attn_over_rels' else self._encoding_dim * 4
atten_dim = self._encoding_dim * 4 + 600
self._merge_atten = TimeDistributed(torch.nn.Linear(atten_dim, self._encoding_dim))
self._residual_encoder = residual_encoder
self._self_attention = LinearMatrixAttention(self._encoding_dim, self._encoding_dim, 'x,y,x*y')
self._merge_self_attention = TimeDistributed(torch.nn.Linear(self._encoding_dim * 3,
self._encoding_dim))
self._span_start_encoder = span_start_encoder
self._span_end_encoder = span_end_encoder
self._span_start_predictor = TimeDistributed(torch.nn.Linear(self._encoding_dim, 1))
self._span_end_predictor = TimeDistributed(torch.nn.Linear(self._encoding_dim, 1))
self._squad_metrics = SquadEmAndF1()
initializer(self)
self._span_start_accuracy = CategoricalAccuracy()
self._span_end_accuracy = CategoricalAccuracy()
self._official_em = Average()
self._official_f1 = Average()
self._span_accuracy = BooleanAccuracy()
self._variational_dropout = InputVariationalDropout(dropout)
Example #6
| Source File: seperate_slqa.py From SLQA with Apache License 2.0 | 4 votes |
|
def __init__(self, vocab: Vocabulary,
elmo_embedder: TextFieldEmbedder,
tokens_embedder: TextFieldEmbedder,
features_embedder: TextFieldEmbedder,
phrase_layer: Seq2SeqEncoder,
projected_layer: Seq2SeqEncoder,
contextual_passage: Seq2SeqEncoder,
contextual_question: Seq2SeqEncoder,
dropout: float = 0.2,
regularizer: Optional[RegularizerApplicator] = None,
initializer: InitializerApplicator = InitializerApplicator(),
):
super(MultiGranularityHierarchicalAttentionFusionNetworks, self).__init__(vocab, regularizer)
self.elmo_embedder = elmo_embedder
self.tokens_embedder = tokens_embedder
self.features_embedder = features_embedder
self._phrase_layer = phrase_layer
self._encoding_dim = self._phrase_layer.get_output_dim()
self.projected_layer = torch.nn.Linear(self._encoding_dim + 1024, self._encoding_dim)
self.fuse_p = FusionLayer(self._encoding_dim)
self.fuse_q = FusionLayer(self._encoding_dim)
self.fuse_s = FusionLayer(self._encoding_dim)
self.projected_lstm = projected_layer
self.contextual_layer_p = contextual_passage
self.contextual_layer_q = contextual_question
self.linear_self_align = torch.nn.Linear(self._encoding_dim, 1)
# self._self_attention = LinearMatrixAttention(self._encoding_dim, self._encoding_dim, 'x,y,x*y')
self._self_attention = BilinearMatrixAttention(self._encoding_dim, self._encoding_dim)
self.bilinear_layer_s = BilinearSeqAtt(self._encoding_dim, self._encoding_dim)
self.bilinear_layer_e = BilinearSeqAtt(self._encoding_dim, self._encoding_dim)
self.yesno_predictor = FeedForward(self._encoding_dim, self._encoding_dim, 3)
self.relu = torch.nn.ReLU()
self._max_span_length = 30
self._span_start_accuracy = CategoricalAccuracy()
self._span_end_accuracy = CategoricalAccuracy()
self._span_accuracy = BooleanAccuracy()
self._squad_metrics = SquadEmAndF1()
self._span_yesno_accuracy = CategoricalAccuracy()
self._official_f1 = Average()
self._variational_dropout = InputVariationalDropout(dropout)
self._loss = torch.nn.CrossEntropyLoss()
initializer(self)
Example #7
| Source File: slqa.py From SLQA with Apache License 2.0 | 4 votes |
|
def __init__(self, vocab: Vocabulary,
text_field_embedder: TextFieldEmbedder,
phrase_layer: Seq2SeqEncoder,
projected_layer: Seq2SeqEncoder,
contextual_passage: Seq2SeqEncoder,
contextual_question: Seq2SeqEncoder,
dropout: float = 0.2,
regularizer: Optional[RegularizerApplicator] = None,
initializer: InitializerApplicator = InitializerApplicator(),
):
super(MultiGranularityHierarchicalAttentionFusionNetworks, self).__init__(vocab, regularizer)
self._text_field_embedder = text_field_embedder
self._phrase_layer = phrase_layer
self._encoding_dim = self._phrase_layer.get_output_dim()
self.projected_layer = torch.nn.Linear(self._encoding_dim + 1024, self._encoding_dim)
self.fuse_p = FusionLayer(self._encoding_dim)
self.fuse_q = FusionLayer(self._encoding_dim)
self.fuse_s = FusionLayer(self._encoding_dim)
self.projected_lstm = projected_layer
self.contextual_layer_p = contextual_passage
self.contextual_layer_q = contextual_question
self.linear_self_align = torch.nn.Linear(self._encoding_dim, 1)
# self.bilinear_self_align = BilinearSelfAlign(self._encoding_dim)
# self._self_attention = LinearMatrixAttention(self._encoding_dim, self._encoding_dim, 'x,y,x*y')
self._self_attention = BilinearMatrixAttention(self._encoding_dim, self._encoding_dim)
self.bilinear_layer_s = BilinearSeqAtt(self._encoding_dim, self._encoding_dim)
self.bilinear_layer_e = BilinearSeqAtt(self._encoding_dim, self._encoding_dim)
self.yesno_predictor = torch.nn.Linear(self._encoding_dim, 3)
self.relu = torch.nn.ReLU()
self._max_span_length = 30
self._span_start_accuracy = CategoricalAccuracy()
self._span_end_accuracy = CategoricalAccuracy()
self._span_accuracy = BooleanAccuracy()
self._squad_metrics = SquadEmAndF1()
self._span_yesno_accuracy = CategoricalAccuracy()
self._official_f1 = Average()
self._variational_dropout = InputVariationalDropout(dropout)
self._loss = torch.nn.CrossEntropyLoss()
initializer(self)
