sdp

sdp

Semantic Dependency Parsing.

class hanlp.components.mtl.tasks.sdp.BiaffineSemanticDependencyParsing(trn: Optional[str] = None, dev: Optional[str] = None, tst: Optional[str] = None, sampler_builder: Optional[hanlp.common.dataset.SamplerBuilder] = None, dependencies: Optional[str] = None, scalar_mix: Optional[hanlp.layers.scalar_mix.ScalarMixWithDropoutBuilder] = None, use_raw_hidden_states=False, lr=0.002, separate_optimizer=False, punct=False, tree=True, pad_rel=None, apply_constraint=False, single_root=True, no_zero_head=None, n_mlp_arc=500, n_mlp_rel=100, mlp_dropout=0.33, mu=0.9, nu=0.9, epsilon=1e-12, decay=0.75, decay_steps=5000, cls_is_bos=True, use_pos=False, **kwargs)[source]

Implementation of “Stanford’s graph-based neural dependency parser at the conll 2017 shared task” (Dozat et al. 2017) and “Establishing Strong Baselines for the New Decade” (He & Choi 2020).

Parameters
  • trn – Path to training set.

  • dev – Path to dev set.

  • tst – Path to test set.

  • sampler_builder – A builder which builds a sampler.

  • dependencies – Its dependencies on other tasks.

  • scalar_mix – A builder which builds a ScalarMixWithDropout object.

  • use_raw_hidden_states – Whether to use raw hidden states from transformer without any pooling.

  • lr – Learning rate for this task.

  • separate_optimizer – Use customized separate optimizer for this task.

  • punctTrue to include punctuations in evaluation.

  • pad_rel – Padding token for relations.

  • apply_constraint – Enforce constraints (see following parameters).

  • single_root – Force single root.

  • no_zero_head – Every token has at least one head.

  • n_mlp_arc – Number of features for arc representation.

  • n_mlp_rel – Number of features for rel representation.

  • mlp_dropout – Dropout applied to MLPs.

  • mu – First coefficient used for computing running averages of gradient and its square in Adam.

  • nu – Second coefficient used for computing running averages of gradient and its square in Adam.

  • epsilon – Term added to the denominator to improve numerical stability

  • decay – Decay rate for exceptional lr scheduler.

  • decay_steps – Decay every decay_steps steps.

  • cls_is_bosTrue to treat the first token as BOS.

  • use_pos – Use pos feature.

  • **kwargs – Not used.

build_dataloader(data, transform: Optional[hanlp.common.transform.TransformList] = None, training=False, device=None, logger: Optional[logging.Logger] = None, gradient_accumulation=1, **kwargs) torch.utils.data.dataloader.DataLoader[source]

Build a dataloader for training or evaluation.

Parameters
  • data – Either a path or a list of samples.

  • transform – The transform from MTL, which is usually [TransformerSequenceTokenizer, FieldLength(‘token’)]

  • training – Whether this method is called on training set.

  • device – The device dataloader is intended to work with.

  • logger – Logger for printing message indicating progress.

  • cache – Whether the dataloader should be cached.

  • gradient_accumulation – Gradient accumulation to be passed to sampler builder.

  • **kwargs – Additional experimental arguments.

build_metric(**kwargs)[source]

Implement this to build metric(s).

Parameters

**kwargs – The subclass decides the method signature.

build_model(encoder_size, training=True, **kwargs) torch.nn.modules.module.Module[source]

Build model.

Parameters
  • trainingTrue if called during training.

  • **kwargs**self.config.

build_optimizer(decoder: torch.nn.modules.module.Module, **kwargs)[source]

Implement this method to build an optimizer.

Parameters

**kwargs – The subclass decides the method signature.

build_samples(inputs, cls_is_bos=False, sep_is_eos=False)[source]

Build samples for this task. Called when this task is the first task. Default behaviour is to take inputs as list of tokens and put these tokens into a dict per sample.

Parameters
  • inputs – Inputs from users, usually a list of lists of tokens.

  • cls_is_bos – Insert BOS to the head of each sentence.

  • sep_is_eos – Append EOS to the tail of each sentence.

Returns

List of samples.

input_is_flat(data) bool[source]

Check whether the data is flat (meaning that it’s only a single sample, not even batched).

Returns

True to indicate the input data is flat.

Return type

bool