A Puzzle-Based Dataset for Natural Language Inference

by   Roxana Szomiu, et al.

We provide here a dataset for tasks related to natural language understanding and natural language inference. The dataset contains logical puzzles in natural language from three domains: comparing puzzles, knighs and knaves, and zebra puzzles. Each puzzle is associated with the entire set of atomic questions that can be generated based on the relations and individuals occurring in the text. For each question we provide the correct answer: entailment, contradiction or ambiguity. The answer's correctness is verified against theorem provers. Good puzzles have two properties: (i) each piece of information is necessary and (ii) no unnecessary information is provided. These properties make puzzles interesting candidates for machine comprehension tasks.


page 1

page 2

page 3

page 4


Using Natural Language Relations between Answer Choices for Machine Comprehension

When evaluating an answer choice for Reading Comprehension task, other a...

Constructing a Natural Language Inference Dataset using Generative Neural Networks

Natural Language Inference is an important task for Natural Language Und...

Logic, Language, and Calculus

The difference between object-language and metalanguage is crucial for l...

Adaptive Artificial Intelligent Q&A Platform

The paper presents an approach to build a question and answer system tha...

Hypothesis Only Baselines in Natural Language Inference

We propose a hypothesis only baseline for diagnosing Natural Language In...

Whodunnit? Crime Drama as a Case for Natural Language Understanding

In this paper we argue that crime drama exemplified in television progra...

Ask, and shall you receive?: Understanding Desire Fulfillment in Natural Language Text

The ability to comprehend wishes or desires and their fulfillment is imp...