Classifying and completing word analogies by machine learning

DOI10.1016/J.IJAR.2021.02.002MaRDI QIDQ2237152zbMATH OpenOpenAlexWikidataFDO

Authors Suryani Lim, Henri Prade, Gilles Richard

Publication date 27 October 2021

Published in International Journal of Approximate Reasoning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ijar.2021.02.002

zbMATH Keywords

analogynatural languageanalogical proportionsword embedding

Mathematics Subject Classification ID

Reasoning under uncertainty in the context of artificial intelligence (68T37)

Recommendations

• Continuous Analogical Proportions-Based Classifier
• Analogy-based classifiers for nominal or numerical data
• A Kolmogorov complexity view of analogy: from logical modeling to experimentations
• A new perspective on analogical proportions
• Analogical proportions

Cites work

• scientific article; zbMATH DE number 5547947 (Why is no real title available?)
• Analogy and Formal Languages
• Analogy between concepts
• Analogy-based classifiers for nominal or numerical data
• From analogical proportion to logical proportions
• Multiple-valued extensions of analogical proportions
• Neural networks and deep learning. A textbook
• Random forests
• Re-representation and creative analogy: a lexico-semantic perspective
• Similarity of semantic relations
• Solving word analogies: a machine learning perspective
• Support-vector networks
• The latent relation mapping engine: algorithm and experiments

Cited in

(5)

• Galois theory for analogical classifiers
• Special issue from the 15th European conference on symbolic and quantitative approaches to reasoning with uncertainty (ECSQARU 2019)
• Revisiting analogical proportions and analogical inference
• Dual embeddings and metrics for word and relational similarity
• Multiple analogical proportions

Describes a project that uses

Uses Software

• word2vec
• Adam
• GloVe
• BERT

This page was built for publication: Classifying and completing word analogies by machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2237152)