Analog retrieval by constraint satisfaction
Artificial Intelligence
Fluid concepts and creative analogies: computer models of the fundamental mechanisms of thought
Fluid concepts and creative analogies: computer models of the fundamental mechanisms of thought
Forgetting Exceptions is Harmful in Language Learning
Machine Learning - Special issue on natural language learning
Reduction Techniques for Instance-BasedLearning Algorithms
Machine Learning
Artificial Intelligence Review - Special issue on lazy learning
Automatic rule induction for unknown-word guessing
Computational Linguistics
Solving analogies on words: an algorithm
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Memory-based morphological analysis
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
CIAA'03 Proceedings of the 8th international conference on Implementation and application of automata
Ripple Down Rule learning for automated word lemmatisation
AI Communications
Analogical Translation of Medical Words in Different Languages
GoTAL '08 Proceedings of the 6th international conference on Advances in Natural Language Processing
Guessers for Finite-State Transducer Lexicons
CICLing '09 Proceedings of the 10th International Conference on Computational Linguistics and Intelligent Text Processing
Improvements in analogical learning: application to translating multi-terms of the medical domain
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Improved morpho-phonological sequence processing with constraint satisfaction inference
SIGPHON '06 Proceedings of the Eighth Meeting of the ACL Special Interest Group on Computational Phonology and Morphology
TextGraphs-3 Proceedings of the 3rd Textgraphs Workshop on Graph-Based Algorithms for Natural Language Processing
Unsupervised morphological analysis by formal analogy
CLEF'09 Proceedings of the 10th cross-language evaluation forum conference on Multilingual information access evaluation: text retrieval experiments
Estimating the proximity between languages by their commonality in vocabulary structures
LTC'09 Proceedings of the 4th conference on Human language technology: challenges for computer science and linguistics
Research on Language and Computation
Evaluation of analogical proportions through Kolmogorov complexity
Knowledge-Based Systems
| Hi-index | 0.00 |
Analogical learning is based on a two-step inference process: (i) computation of a structural mapping between a new and a memorized situation; (ii) transfer of knowledge from the known to the unknown situation. This approach requires the ability to search for and exploit such mappings, hence the need to properly define analogical relationships, and to efficiently implement their computation. In this paper, we propose a unified definition for the notion of (formal) analogical proportion, which applies to a wide range of algebraic structures. We show that this definition is suitable for learning in domains involving large databases of structured data, as is especially the case in Natural Language Processing (NLP). We then present experimental results obtained on two morphological analysis tasks which demonstrate the flexibility and accuracy of this approach.