Automatic Identification of Equivalence of Concepts in Different Languages for Never-Ending Learning

• Silvio C. Marino UFSCAR
• Estevam R. Hruschka Junior UFSCAR

DOI: https://doi.org/10.5753/eniac.2018.4412

Resumo

This paper describes the process of automatic identification of concepts in different languages using a base that relies on simple semantic and morphosyntactic characteristics like string similarity, difference in words amount and translation position on dictionary (when exists) and a neural network that has been used as a model of machine learning. All experiments use data that was obtained from a few categories of Read The Web (RTW) project and an endless learning computation system called NELL: Never-Ending Language Learning. The results were compared with dictionary and showed that the introduction of neural network brought a significant gain in the process of equivalence of concepts.

Referências

Duarte M.C. (2011). “Aprendizado Semissupervisionado através de técnicas de acoplamento”, https://repositorio.ufscar.br/bitstream/handle/ufscar/474/3777.pdf.

Duarte M.C. (2014). Exploring two Views of Coreference Resolution in a Never-Ending Learning System. In International Conference on Hybrid Intelligent Systems (HIS).

González J., Hruschka E.R., Mitchell T.M (2017) “Merging Knowledge bases in different languages”, http://www.aclweb.org/anthology/W17- 2403

Haykin, S. (1999) “Neural Networks: A Comprehensive Foundation”, bookman, ed. 2, Hamilton, Ontario, Canada.

Ke Y., Hagiwara M. (2015). A Natural Language Processing Neural Network Comprehending English. In International Joint Conference on Neural Networks (IJCNN), https://ieeexplore.ieee.org/abstract/document/7280492/

Kurzweil, R. (1990) “The Age of Spiritual Machines”, The MIT Press, Massachusetts.

Mitchell, T.M. (1997) “Machine Learning”, McGraw-Hill, 1. ed., New York, NY, USA.

Mitchell, T.M. et al (2018). Never-ending learning. In Communications of the ACM, v. 61, pages 103-115.

Wijaya, D.T., Mitchell T.M. (2016) Mapping Verbs in Different Languages to Knowledge Base Relations using Web Text as Interlingua. In: HLT-NAACL.

Zhu, X. et al (2003). Semi-supervised learning using gaussian fields and harmonic functions. In Machine Learning-International Workshop Then Conference, v. 20, n. 2, page 912.