fibber.metrics.classifier.fasttext_classifier module

class fibber.metrics.classifier.fasttext_classifier.FasttextClassifier(dataset_name, trainset, testset, fasttext_lr=1.0, fasttext_epoch=25, fasttext_ngram=5, **kwargs)

Bases: fibber.metrics.classifier.classifier_base.ClassifierBase

fasttext classifier prediction on paraphrase_list.

This metric is special, it does not compare the original and paraphrased sentence. Instead, it outputs the classifier prediction on paraphrase_list. So we should not compute mean or std on this metric.

Parameters

• dataset_name (str) – the name of the dataset.

• trainset (dict) – a fibber dataset.

• testset (dict) – a fibber dataset.

• fasttext_lr (float) – learning rate.

• fasttext_epoch (int) – epochs to train.

• fasttext_ngram (int) – classification feature ngram.

load_robust_tuned_model(save_path)

robust_tune_init(optimizer, lr, weight_decay, steps)

robust_tune_step(data_record_list)

save_robust_tuned_model(load_path)

fibber.metrics.classifier.fasttext_classifier.change_to_fasttext_format(dataset, filename)

Change Fibber’s dataset to fast text’s format and save to a file.

previous

fibber.metrics.classifier.classifier_base module

next

fibber.metrics.classifier.input_manipulation_classifier module