Weighted automata extraction and explanation of recurrent neural networks for natural language tasks

DOI10.1016/J.JLAMP.2023.100907arXiv2306.14040OpenAlexW4386493292MaRDI QIDQ6151603

Yi-Hao Zhang, Xiyue Zhang, Meng Sun, Zeming Wei

Publication date: 12 February 2024

Published in: Journal of Logical and Algebraic Methods in Programming (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2306.14040

zbMATH Keywords

explanationrecurrent neural networksabstractionweighted finite automatanatural languages

Mathematics Subject Classification ID

Computer science (68-XX)

Cites Work

• The Jensen-Shannon divergence
• Learning regular sets from queries and counterexamples
• Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review
• Unnamed Item

This page was built for publication: Weighted automata extraction and explanation of recurrent neural networks for natural language tasks