Extraction and Systematic Synthesis of Textual Information by Contextualization and Enrichment : Applications of Automated Reasoning in the Cognitive Sciences

  • John Bagiliko African Institute for Mathematical Sciences - AIMS Senegal
  • Kaninda MUSUMBU Labri - Université Bordeaux
  • Saliou Diouf
Keywords: Artificial Intelligence, Commonsense Reasoning, Automated Reasoning, Language Models, Wingograd Schema

Abstract

One of the major problems in AI and Deep Learning is Commonsense Reasoning. As easy as it is for humans to perform certain tasks without having to think and waste much time, machines have difficulties in performing those tasks without necessarily been programmed.The Winograd schema is one of the recommended ways for testing the Commonsense reasoning ability of machines. It is difficult for machines to answer this Winograd Schema. In this work, we propose the use of neural network based on Language Models in tackling this problem. Our network takes in only word inputs for the training on large vocabulary size. This model attains an accuracy of
54.58 percent when ran on the Winograd Schema Challenge.

Downloads

Download data is not yet available.

Author Biographies

John Bagiliko, African Institute for Mathematical Sciences - AIMS Senegal

AIMS, Km2 route de Joal (Centre IRD), B.P. 1418, Mbour - Senegal

Kaninda MUSUMBU, Labri - Université Bordeaux

Labri - Université Bordeaux 1 351, cours de la Libération 33405 TALENCE Cedex

Saliou Diouf

AIMS, Km2 route de Joal (Centre IRD), B.P. 1418, Mbour - Senegal

 

References

D. L. Poole and A. K. Mackworth, Artificial Intelligence: Foundations of Computational Agents CAMBRIDGE UNIVERSITY PRESS, NY,USA, 2010.

D. Sarkar, R. Bali and T. Sharma, Practical Machine Learning with Python: A Problem-Solvers Guide to Building Real-World Intelligent Systems Springer Science, New York, USA, 2018.

D. Sarkar, Text Analytics with Python: A Practical Real-World Approach to Gaining Actionable Insights from your Data Apress, Berkeley,CA, 2016.

E. Davis and G. Marcus, COMMUNICATIONS OF THE ACM 58, 92 (2015).

R. Nakatsu, DIAGRAMMATIC REASONING IN AI John Wiley and Sons, Inc., Hoboken, New Jersey, 2010.

M. P. Bonacina and A. Martelli, Intelligenza Artificiale 3, 14 (2006).

J. McCarthy, Artificial Intelligence, Logic and Formalizing Common Sense (In: Thomason R.H. (eds) Philosophical Logic and Artificial Intelligence. Springer, Dordrecht, 1989).

Y. Jernite, D. Sontag, and A. M. Rus, CoRR abs/1508.06615,(2018).

S. Ye, T. Chua, M. Kan, and L. Qiu, Information Processing and Management 43, 1463 (2007).

T. H. Trinh and Q. V. Le, A Simple Method for Commonsense Reasoning (2018).

Bies, Ann, J. Mott and C. Warner, English News Text Treebank: Penn Treebank Web Download. Philadelphia: Linguistic Data Consortium, 2015.

G. Yoav Neural Network Methods for Natural Language Processing , 2017.

Published
2019-07-26
How to Cite
Bagiliko, J., Kaninda MUSUMBU, & Saliou Diouf. (2019). Extraction and Systematic Synthesis of Textual Information by Contextualization and Enrichment : Applications of Automated Reasoning in the Cognitive Sciences. IJRDO - Journal of Mathematics (ISSN: 2455-9210), 5(7), 01-08. Retrieved from https://ijrdo.org/index.php/m/article/view/3004