fibber.metrics.similarity.ce_similarity_metric module

This metric computes the embedding similarity using SBERT model.

class fibber.metrics.similarity.ce_similarity_metric.CESimilarityMetric(ce_pretrained_model='stsb-roberta-large', ce_gpu_id=- 1, **kwargs)[source]

Bases: fibber.metrics.metric_base.MetricBase

This metric computes the semantic similarity of two sentences using Cross Encoder model.

By default the we use stsb-roberta-large model.

see https://github.com/UKPLab/sentence-transformers for more information.

Initialize ce model.

previous

fibber.metrics.similarity package

next

fibber.metrics.similarity.glove_similarity_metric module