A Deep Learning Approach to Solving Morphological Analogies

First published in
Lecture notes in computer science  
Number in series
13405 LNAI
Start Page
159
End Page
174
Citation
Lecture notes in computer science 13405 LNAI: 159-174 (2022)
Contribution to Conference
30th International Conference on Case-Based Reasoning, ICCBR 2022  
Publisher DOI
10.1007/978-3-031-14923-8_11
Scopus ID
2-s2.0-85136925142
Publisher
Springer
Analogical proportions are statements of the form “A is to B as C is to D”. They support analogical inference and provide a logical framework to address learning, transfer, and explainability concerns. This logical framework finds useful applications in AI and natural language processing (NLP). In this paper, we address the problem of solving morphological analogies using a retrieval approach named ANNr. Our deep learning framework encodes structural properties of analogical proportions and relies on a specifically designed embedding model capturing morphological characteristics of words. We demonstrate that ANNr outperforms the state of the art on 11 languages. We analyze ANNr results for Navajo and Georgian, languages on which the model performs worst and best, to explore potential correlations between the mistakes of ANNr and linguistic properties.
Subjects
Analogy solving
Morphological word embeddings
Neural networks
Retrieval