Contract NLI (Natural Language Inference)

ContractNLI is originally a dataset for document-level natural language inference (NLI) on contracts whose goal is to automate/support a time-consuming procedure of contract review. A system is given a set of hypotheses and a contract, and it is asked to classify whether each hypothesis is entailed by, contradicting to or not mentioned by (neutral to) the contract as well as identifying evidence for the decision as spans in the contract. The version of the dataset presented here is tailored for multi-label text classification. The hypotheses are mapped to categories (labels), and the evidence in the contract are the phrases that are associated (labeled) with these categories.