A Fine-grained Interpretability Evaluation Benchmark for Neural NLP

41649

Back to Articles Dashboard

Knowledge Triples

Source Entity	Relationship	Target Entity
Benchmark Material	covers	Reading Comprehension Task
Benchmark Material	covers	Sentiment Analysis Task
Benchmark Material	covers	Textual Similarity Task
Benchmark Material	provides	Rationale OtherEntity
Interpretability Metric	evaluatedBy	Benchmark Material
Rationale OtherEntity	evaluates	Consistency Metric Metric