On the Transferability of Neural Models of Morphological Analogies
This addresses the challenge of morphological reasoning in NLP for multilingual applications, but it is incremental as it applies existing deep learning methods to a specific task.
The paper tackled the problem of detecting morphological analogies using a deep learning approach, and found that the framework transfers across languages with interesting similarities and differences, enabling discussion on building a multilingual model.
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.