AMR4NLI: Interpretable and robust NLI measures from semantic graphs
Abstract
The task of natural language inference (NLI) asks whether a given premise (expressed in NL) entails a given NL hypothesis. NLI benchmarks contain human ratings of entailment, but the meaning relationships driving these ratings are not formalized. Can the underlying sentence pair relationships be made more explicit in an interpretable yet robust fashion? We compare semantic structures to represent premise and hypothesis, including sets of contextualized embeddings and semantic graphs (Abstract Meaning Representations), and measure whether the hypothesis is a semantic substructure of the premise, utilizing interpretable metrics. Our evaluation on three English benchmarks finds value in both contextualized embeddings and semantic graphs; moreover, they provide complementary signals, and can be leveraged together in a hybrid model.
Cite
@article{arxiv.2306.00936,
title = {AMR4NLI: Interpretable and robust NLI measures from semantic graphs},
author = {Juri Opitz and Shira Wein and Julius Steen and Anette Frank and Nathan Schneider},
journal= {arXiv preprint arXiv:2306.00936},
year = {2023}
}
Comments
International Conference on Computational Semantics (IWCS 2023); v2 fixes an imprecise sentence below Eq. 5