def _get_model(self) -> nn.Module:
word_embedder = TrainableWordEmbedder(
embedding_type=self.hparams.get("emb_type"),
datasets_manager=self.data_manager,
)
elmo_embedder = BowElmoEmbedder(datasets_manager=self.data_manager,
layer_aggregation="sum")
embedder = ConcatEmbedders([word_embedder, elmo_embedder])
lstm2seqencoder = Lstm2SeqEncoder(
embedder=embedder,
hidden_dim=self.hparams.get("hidden_dim"),
bidirectional=self.hparams.get("bidirectional"),
combine_strategy=self.hparams.get("combine_strategy"),
rnn_bias=True,
dropout_value=self.hparams.get("lstm2seq_dropout", 0.0),
add_projection_layer=False,
)
model = RnnSeqCrfTagger(
rnn2seqencoder=lstm2seqencoder,
encoding_dim=2 *
self.hparams.get("hidden_dim") if self.hparams.get("bidirectional")
and self.hparams.get("combine_strategy") == "concat" else
self.hparams.get("hidden_dim"),
datasets_manager=self.data_manager,
)
return model
def build_model(self):
embedder = TrainableWordEmbedder(
embedding_type=self.hparams.get("emb_type"),
datasets_manager=self.data_manager,
device=self.hparams.get("device"),
)
embedder = ConcatEmbedders([embedder])
lstm2seqencoder = Lstm2SeqEncoder(
embedder=embedder,
dropout_value=self.hparams.get("dropout"),
hidden_dim=self.hparams.get("hidden_dim"),
bidirectional=self.hparams.get("bidirectional"),
combine_strategy=self.hparams.get("combine_strategy"),
rnn_bias=True,
device=self.hparams.get("device"),
num_layers=self.hparams.get("num_layers"),
)
model = RnnSeqCrfTagger(
rnn2seqencoder=lstm2seqencoder,
encoding_dim=2 * self.hparams.get("hidden_dim")
if self.hparams.get("bidirectional")
and self.hparams.get("combine_strategy") == "concat"
else self.hparams.get("hidden_dim"),
device=self.hparams.get("device"),
tagging_type="IOB1",
datasets_manager=self.data_manager,
)
return model
def build_science_ie_model(dirname: str):
exp_dirpath = pathlib.Path(dirname)
data_dir = pathlib.Path(DATA_DIR)
train_filename = data_dir.joinpath("train_science_ie_conll.txt")
dev_filename = data_dir.joinpath("dev_science_ie_conll.txt")
test_filename = data_dir.joinpath("dev_science_ie_conll.txt")
data_manager = CoNLLDatasetManager(
train_filename=train_filename,
dev_filename=dev_filename,
test_filename=test_filename,
column_names=["TASK", "PROCESS", "MATERIAL"],
)
word_embedder = TrainableWordEmbedder(
embedding_type="glove_6B_100", datasets_manager=data_manager
)
char_embedder = CharEmbedder(
char_embedding_dimension=20, hidden_dimension=25, datasets_manager=data_manager
)
embedder = ConcatEmbedders([word_embedder, char_embedder])
lstm2seqencoder = Lstm2SeqEncoder(
embedder=embedder,
hidden_dim=350,
bidirectional=True,
combine_strategy="concat",
rnn_bias=True,
device=torch.device("cpu"),
num_layers=2,
)
model = RnnSeqCrfTagger(
rnn2seqencoder=lstm2seqencoder,
encoding_dim=700,
datasets_manager=data_manager,
namespace_to_constraints=None,
tagging_type="BIOUL",
)
infer = SequenceLabellingInference(
model=model,
model_filepath=str(exp_dirpath.joinpath("checkpoints", "best_model.pt")),
datasets_manager=data_manager,
)
return infer
def build_model(self):
word_embedder = TrainableWordEmbedder(
embedding_type=self.hparams.get("emb_type"),
datasets_manager=self.data_manager,
)
char_embedder = CharEmbedder(
char_embedding_dimension=self.hparams.get("char_emb_dim"),
hidden_dimension=self.hparams.get("char_encoder_hidden_dim"),
datasets_manager=self.data_manager,
)
elmo_embedder = BowElmoEmbedder(datasets_manager=self.data_manager)
embedder = ConcatEmbedders([word_embedder, char_embedder, elmo_embedder])
lstm2seqencoder = Lstm2SeqEncoder(
embedder=embedder,
hidden_dim=self.hparams.get("hidden_dim"),
bidirectional=self.hparams.get("bidirectional"),
combine_strategy=self.hparams.get("combine_strategy"),
rnn_bias=True,
)
model = RnnSeqCrfTagger(
rnn2seqencoder=lstm2seqencoder,
encoding_dim=2 * self.hparams.get("hidden_dim")
if self.hparams.get("bidirectional")
and self.hparams.get("combine_strategy") == "concat"
else self.hparams.get("hidden_dim"),
datasets_manager=self.data_manager,
)
self.printer.good("Finished Loading the Model")
return model
args = parser.parse_args()
msg_printer = wasabi.Printer()
DATA_DIR = pathlib.Path(DATA_DIR)
train_filename = DATA_DIR.joinpath("train_science_ie_conll.txt")
dev_filename = DATA_DIR.joinpath("dev_science_ie_conll.txt")
data_manager = CoNLLDatasetManager(
train_filename=train_filename,
dev_filename=dev_filename,
test_filename=dev_filename,
column_names=["TASK", "PROCESS", "MATERIAL"],
)
embedder = TrainableWordEmbedder(embedding_type=args.emb_type,
datasets_manager=data_manager,
device=args.device)
char_embedder = CharEmbedder(
char_embedding_dimension=args.char_emb_dim,
hidden_dimension=args.char_encoder_hidden_dim,
datasets_manager=data_manager,
device=args.device,
)
embedder = ConcatEmbedders([embedder, char_embedder])
lstm2seqencoder = Lstm2SeqEncoder(
embedder=embedder,
dropout_value=args.dropout,
hidden_dim=args.hidden_dim,
bidirectional=args.bidirectional,
def setup_embedder(setup_parscit_dataset_manager, request):
data_manager = setup_parscit_dataset_manager
embedding_type = request.param
embedder = TrainableWordEmbedder(datasets_manager=data_manager,
embedding_type=embedding_type)
return embedder, data_manager
lstm2seqencoder = Lstm2SeqEncoder(
embedder=embedder,
dropout_value=args.dropout,
hidden_dim=args.hidden_dim,
bidirectional=args.bidirectional,
combine_strategy=args.combine_strategy,
rnn_bias=True,
device=args.device,
num_layers=args.num_layers,
add_projection_layer=args.add_projection_layer,
)
attn = DotProductAttention()
context_embedder = TrainableWordEmbedder(
embedding_type="glove_6B_300", datasets_manager=data_manager, device=args.device
)
lstm2seq_attn_encoder = Lstm2SeqAttnContextEncoder(
rnn2seqencoder=lstm2seqencoder,
attn_module=attn,
context_embedder=context_embedder,
device=args.device,
)
model = RnnSeqCrfTagger(
rnn2seqencoder=lstm2seq_attn_encoder,
encoding_dim=600,
device=args.device,
tagging_type="BIOUL",
datasets_manager=data_manager,
include_start_end_trainsitions=False,
)
