Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehension (MRC) or natural language inference (NLI). We introduce SpanEx, a multi-annotator dataset of human-annotated span interaction explanations for two NLU tasks: NLI and FC.
SpanEx - consists of 7071 instances annotated for span interactions. - the first dataset with human phrase-level interaction explanations with explicit labels for interaction types. - annotated by three annotators, which opens new avenues for studies of human explanation agreement -- an understudied area in the explainability literature.
Paper | Code | Results | Date | Stars |
---|