# A corpus of precise natural textual entailment problems

## TL;DR

This paper introduces a new, precise corpus of 150 natural language entailment problems derived from real-world texts, aiming to improve the testing of natural-language inference systems.

## Contribution

It presents a novel corpus that combines precision, real-world relevance, and expert-verified hypotheses for natural language entailment evaluation.

## Key findings

- Corpus contains 150 problems from real-world texts
- Problems include implicit hypotheses identified by experts
- First step towards comprehensive testing of inference systems

## Abstract

In this paper, we present a new corpus of entailment problems. This corpus combines the following characteristics: 1. it is precise (does not leave out implicit hypotheses) 2. it is based on "real-world" texts (i.e. most of the premises were written for purposes other than testing textual entailment). 3. its size is 150. The corpus was constructed by taking problems from the Real Text Entailment and discovering missing hypotheses using a crowd of experts. We believe that this corpus constitutes a first step towards wide-coverage testing of precise natural-language inference systems.