ICESBA - Submit a paper, International Conference on Economic Sciences and Business Administration

Font Size: 
Self-learning improvement by means of cloud computing
Crina Narcisa Deac, Gicu Călin DEAC, Costel Emil Cotet, Mihalache GHINEA

Last modified: 2018-01-12


This paper describes some results of authors' research in machine reading at scale as a support for self-learning, which combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF (term frequency–inverse document frequency) matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs.


self-learning, NLP, machine learning


  1. Leadbeater, C. and Wong, A. 2010. Learning from the Extremes: A White Paper. San Jose, Calif., Cisco Systems Inc.  (Accessed 4 september 2017).
  2. Robinson, K. 2006. How schools kill creativity (online video). TED Conference 2006. Monterey, Calif. (Accessed 5 september 2017).
  3. Redecker, C., Ala-Mutka, K., Leis, M., Leendertse, M., Punie, Y., Gijsbers, G., Kirschner, P., Stoyanov, S. and Hoogveld, B. 2011. The Future of Learning: Preparing for Change. Luxembourg, Publications Office of the European Union. (Accessed 5 septemberl 2017).
  4. Tensors and Dynamic neural networks in Python with strong GPU acceleration.  (Accessed 1 september 2017)
  5. Stanford CoreNLP – Natural language software   (Accessed 1 september 2017)
  6. Industrial-Strength Natural Language Processing in Python   (Accessed 1 september 2017)
  7. Natural Language Toolkit - RegexpTokenizer  (Accessed 1 september 2017)
  8. Chris Manning – How computers are learning to understand language (Accessed 3 september 2017)
  9. Hai Wang Mohit Bansal Kevin Gimpel David McAllester (2015) Machine Comprehension with Syntax, Frames, and Semantics, Toyota Technological Institute at Chicago, Chicago, IL, 60637, USA

Full Text: PDF