capreolus.reranker.CEDRKNRM

Module Contents

Classes

CEDRKNRM_Class
CEDRKNRM	Base class for Reranker modules. The purpose of a Reranker is to predict relevance scores for input documents. Rerankers are generally supervised methods implemented in PyTorch or TensorFlow.

capreolus.reranker.CEDRKNRM.logger

class capreolus.reranker.CEDRKNRM.CEDRKNRM_Class(extractor, config, *args, **kwargs)

Bases: torch.nn.Module

masked_simmats(self, embeddings, bert_mask, bert_segments)

knrm(self, bert_output, bert_mask, bert_segments, batch_size)

forward(self, bert_input, bert_mask, bert_segments)

class capreolus.reranker.CEDRKNRM.CEDRKNRM(config=None, provide=None, share_dependency_objects=False, build=True)

Bases: capreolus.reranker.Reranker

Base class for Reranker modules. The purpose of a Reranker is to predict relevance scores for input documents. Rerankers are generally supervised methods implemented in PyTorch or TensorFlow.

Modules should provide:

• a build_model method that initializes the model used

• a score and a test method that take a representation created by an Extractor module as input and return document scores

• a load_weights and a save_weights method, if the base class’ PyTorch methods cannot be used

module_name = CEDRKNRM

dependencies

config_spec

build_model(self)

score(self, d)

test(self, d)