Deep Learning Powered Question-Answering Framework for Organizations Digital Transformation

In the context of digital transformation by governments, the public sector and other organizations, many information is moving to digital platforms. Chatbots and similar question-answering systems are becoming popular to answer information queries, opposed to browsing online repositories or webpages. State-of-the-art approaches for these systems may be laborious to implement, hard to train and maintain, and also require a high level of expertise. This work explores the definition of a generic framework to systematically build question-answering systems. A sandbox implementation of this framework enables the deployment of turnkey systems, directly from already existing collections of documents. These systems can then be used to provide a question-answering system communication channel to enrich the organization digital presence.

[1]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[2]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[3]  Javier Bermejo Razquin.  A friendly approach to Open Government: Chatbots , 2018 .

[4]  Peter Wiemer-Hastings,et al.  Latent semantic analysis , 2004, Annu. Rev. Inf. Sci. Technol..

[5]  James H. Martin,et al.  Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition , 2000 .

[6]  Bowen Zhou,et al.  Applying deep learning to answer selection: A study and an open task , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[7]  Cordelia V. Hall,et al.  Introduction to Haskell , 2000 .

[8]  Ruslan Salakhutdinov,et al.  Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text , 2018, EMNLP.

[9]  Daniel A. Keim,et al.  Mastering the Information Age - Solving Problems with Visual Analytics , 2010 .

[10]  Luís Soares Barbosa,et al.  Transforming Legal Documents for Visualization and Analysis , 2018, ICEGOV.

[11]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[12]  Ali Farhadi,et al.  Bidirectional Attention Flow for Machine Comprehension , 2016, ICLR.

[13]  Tomasz Janowski,et al.  Digital Government and Administrative Burden Reduction , 2016, ICEGOV.

[14]  Geoffrey Zweig,et al.  Attention with Intention for a Neural Network Conversation Model , 2015, ArXiv.