Explainable lexical entailment with semantic graphs

We present novel methods for detecting lexical entailment in a fully rule-based and explainable fashion, by automatic construction of semantic graphs, in any language for which a crowd-sourced dictionary with sufficient coverage and a dependency parser of sufficient accuracy are available. We experi...

Full description

Saved in:
Bibliographic Details
Published in:Natural language engineering 2023-09, Vol.29 (5), p.1223-1246
Main Authors: Kovacs, Adam, Gemes, Kinga, Kornai, Andras, Recski, Gabor
Format: Article
Language:English
Subjects:
Benchmarks
Candidates
Computational linguistics
Datasets
Deep learning
Dictionaries
Entailment
Error analysis
Graphs
Hypotheses
Inference
Language
Lexical semantics
Linguistics
Multilingualism
Natural language
Open source software
Parsing
Semantics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present novel methods for detecting lexical entailment in a fully rule-based and explainable fashion, by automatic construction of semantic graphs, in any language for which a crowd-sourced dictionary with sufficient coverage and a dependency parser of sufficient accuracy are available. We experiment and evaluate on both the Semeval-2020 lexical entailment task (Glavaš et al. (2020). Proceedings of the Fourteenth Workshop on Semantic Evaluation, pp. 24–35) and the SherLIiC lexical inference dataset of typed predicates (Schmitt and Schütze (2019). Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 902–914). Combined with top-performing systems, our method achieves improvements over the previous state-of-the-art on both benchmarks. As a standalone system, it offers a fully interpretable model of lexical entailment that makes detailed error analysis possible, uncovering future directions for improving both the semantic parsing method and the inference process on semantic graphs. We release all components of our system as open source software.
ISSN:1351-3249
1469-8110
DOI:10.1017/S1351324922000092