Analogies

An analogical proportion is a statement of the form "A is to B as C is to D", written "A : B :: C : D". The underlying idea is that the relation between A and B is similar to the one between C and D.

On the one hand, analogical proportions ground analogical inference that has been used in various machine learning tasks such as classification, decision making, and automatic translation, with competitive results. On the other hand, they support analogical extrapolation that can be used to solve hard reasoning tasks, such as IQ tests. It can also be used in data augmentation, especially in learning environments with few labeled samples.

What makes reasoning with analogies special is its ability to process simultaneously similarities and dissimilarities. This characteristic establishes bridges between the two main axes of AI: knowledge representation and reasoning (KRR) and machine learning (ML). Analogical reasoning contributes to a transparent AI as it is close to human reasoning and provides explanations based on examples and counter-examples. The objective of the ANNa project is to provide an online platform to detect, solve, and reason on analogies, with multiple applications in various domains, for instance, in NLP, biomedical sciences, as well as in industry.

Morphological Analogy Proportions

Morphological analogies are analogical proportions between words, that encapsulate the morphological features of the words. For example: Star : Stars :: Moon : Moons is a morphological analogy proportion.

To resolve them, we propose ANNa-MD (MD for Morphological analogy Detection), an approach using deep learning to identify morphological analogies based on a specific embedding model that captures morphological characteristics of words.

We also introduce ANNa-MR (MR for Morphological analogy Resolution), an approach using deep learning to infer the missing element of a morphological analogy. Our models displays competitive performance on analogy resolution and analogy detection over multiple languages.

Resolve Morphological Analogies Online

Semantical Analogy Proportions

Semantical analogies are analogical proportions between words based on the meaning and semantic relation between words. For example: Paris : France :: Berlin : Germany is a semantical analogy proportion.

We propose using a zero-shot quantized version of Mistral-7B instruct, a small and faster variant of Mistral's original models, to address both semantic analogy detection and semantic analogy resolution tasks.

Resolve Semantical Analogies Online