textflint.generation_layer.transformation.NLI.overlap

Generate some samples by templates

implement follow Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference ACL2019 In order to generate some sample whose premise is the sequence of the hypothesis but the semantic are different.

---

class textflint.generation_layer.transformation.NLI.overlap.Overlap

Bases: textflint.generation_layer.transformation.transformation.Transformation

Generate some samples by templates

implement follow Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference ACL2019 In order to generate some sample whose premise is the sequence of the hypothesis but the semantic are different. exmaple: {

hypothesis: I hope Tom can go to school. premise: Tom goes to school. y: contradicion

}

transform(sample, n=1, **kwargs)

Transform data sample to a list of Sample.

Parameters

• sample (~NLISample) – Data sample for augmentation

• n (int) – Default is 1. MAX number of unique augmented output

• **kwargs –

Returns

Augmented data

class textflint.generation_layer.transformation.NLI.overlap.Transformation(**kwargs)

Bases: abc.ABC

An abstract class for transforming a sequence of text to produce a list of potential adversarial example.

processor = <textflint.common.preprocess.en_processor.EnProcessor object>

transform(sample, n=1, field='x', **kwargs)

Transform data sample to a list of Sample.

Parameters

• sample (Sample) – Data sample for augmentation.

• n (int) – Max number of unique augmented output, default is 5.

• field (str|list) – Indicate which fields to apply transformations.

• **kwargs (dict) –

  other auxiliary params.

Returns

list of Sample

classmethod sample_num(x, num)

Get ‘num’ samples from x.

Parameters

• x (list) – list to sample

• num (int) – sample number

Returns

max ‘num’ unique samples.