Journal article
Zaid Marji, Animesh Nighojkar, John Licato
The Florida AI Research Society, 2020
The Florida AI Research Society, 2020
Semantic Scholar
ArXiv
DBLP
Cite
Cite
APA
Click to copy
Marji, Z., Nighojkar, A., & Licato, J. (2020). Probing the Natural Language Inference Task with Automated Reasoning Tools. The Florida AI Research Society.
Chicago/Turabian
Click to copy
Marji, Zaid, Animesh Nighojkar, and John Licato. “Probing the Natural Language Inference Task with Automated Reasoning Tools.” The Florida AI Research Society (2020).
MLA
Click to copy
Marji, Zaid, et al. “Probing the Natural Language Inference Task with Automated Reasoning Tools.” The Florida AI Research Society, 2020.
BibTeX Click to copy
@article{zaid2020a,
title = {Probing the Natural Language Inference Task with Automated Reasoning Tools},
year = {2020},
journal = {The Florida AI Research Society},
author = {Marji, Zaid and Nighojkar, Animesh and Licato, John}
}
Abstract
The Natural Language Inference (NLI) task is an important task in modern NLP, as it asks a broad question to which many other tasks may be reducible: Given a pair of sentences, does the first entail the second? Although the state-of-the-art on current benchmark datasets for NLI are deep learning-based, it is worthwhile to use other techniques to examine the logical structure of the NLI task. We do so by testing how well a machine-oriented controlled natural language (Attempto Controlled English) can be used to parse NLI sentences, and how well automated theorem provers can reason over the resulting formulae. To improve performance, we develop a set of syntactic and semantic transformation rules. We report their performance, and discuss implications for NLI and logic-based NLP.
