Work

Breaking NLI Systems with Sentences that Require Simple Lexical Inferences

Year: 2018

Type: conference-paper

Abstract: We create a new NLI test set that shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge.The new examples are simpler than the SNLI test set, containing sentences that differ by at most one word from sentences in the training set.Yet, the performance on the new test set is substantially worse across systems trained on SNLI, demonstrating that these systems are limited in their generalization ability, failing to capture many simple inferences.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/p18-2103

Authors: Max Glockner, Vered Shwartz, Yoav Goldberg

Institutions: Technische Universität Darmstadt, Bar-Ilan University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Deutsche Forschungsgemeinschaft, Israel Science Foundation, Intel Collaboration Research Institute for Computational Intelligence

Award: G7805275943