Title : Analogies and deep learning: case study of word morphology
An analogy, or more specifically an analogical proportion, is a relation between four elements A, B, C, and D meaning "A is to B as C is to D", often written as A:B::C:D.
For example, "cat : kitten :: dog : puppy" and "cat : cats :: dog : dogs" are two analogies between words. Notice that the transformation between "cat" and "kitten" is a semantic one (i.e. on the meaning: "kitten" is a young "cat") while the one between "cat" and "cats" is morphological (i.e. on the structure of the words: "cats" is the plural of "cat", obtained with the suffix "-s"). We call the first example a "semantic analogy" and the second a "morphological analogy".
Tackling morphological analogies automatically is way less trivial than appears at first sight, as morphology behaves differently on different languages and covers both simple and complex phenomena. A framework of deep (and not so deep) learning was designed to tackle multiple aspects of these analogies on different languages, outperforming symbolic baselines by a wide margin. We will first describe the key features of the results and some of our key results, and discuss multiple potential applications of the framework on other domains such as medical data, knowledge representation or sentence-level semantics. Finally, we will mention some of the key theoretical concerns to improve how machine learning can be used for analogy, and how analogy can be used for machine learning.