DeepAI AI Chat
Log In Sign Up

A large annotated corpus for learning natural language inference

by   Samuel R. Bowman, et al.
Stanford University

Understanding entailment and contradiction is fundamental to understanding natural language, and inference about entailment and contradiction is a valuable testing ground for the development of semantic representations. However, machine learning research in this area has been dramatically limited by the lack of large-scale resources. To address this, we introduce the Stanford Natural Language Inference corpus, a new, freely available collection of labeled sentence pairs, written by humans doing a novel grounded task based on image captioning. At 570K pairs, it is two orders of magnitude larger than all other resources of its type. This increase in scale allows lexicalized classifiers to outperform some sophisticated existing entailment models, and it allows a neural network-based model to perform competitively on natural language inference benchmarks for the first time.


page 1

page 2

page 3

page 4


Visual Entailment Task for Visually-Grounded Language Learning

We introduce a new inference task - Visual Entailment (VE) - which diffe...

Generating Natural Language Inference Chains

The ability to reason with natural language is a fundamental prerequisit...

Natural Language Inference over Interaction Space

Natural Language Inference (NLI) task requires an agent to determine the...

Semantic Matching Against a Corpus: New Applications and Methods

We consider the case of a domain expert who wishes to explore the extent...

A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference

This paper introduces the Multi-Genre Natural Language Inference (MultiN...

Modular Representation Underlies Systematic Generalization in Neural Natural Language Inference Models

In adversarial (challenge) testing, we pose hard generalization tasks in...

A corpus of precise natural textual entailment problems

In this paper, we present a new corpus of entailment problems. This corp...