On the Transferability of Neural Models of Morphological Analogies

First published in
Communications in Computer and Information Science  
Number in series
1524 CCIS
Start Page
76
End Page
89
Citation
Communications in Computer and Information Science 1524: 76-89 (2021)
Contribution to Conference
21st European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2021  
Publisher DOI
10.1007/978-3-030-93736-2_7
Scopus ID
2-s2.0-85126245459
Publisher
Springer International Publishing
Analogical proportions are statements expressed in the form “A is to B as C is to D” and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). In this paper, we focus on morphological tasks and we propose a deep learning approach to detect morphological analogies. We present an empirical study to see how our framework transfers across languages, and that highlights interesting similarities and differences between these languages. In view of these results, we also discuss the possibility of building a multilingual morphological model.
Subjects
Analogy classification
Deep learning
Morphological analogy
Transferability