Publication Type : Conference Paper
Publisher : Springer Verlag
Source : Lecture Notes in Electrical Engineering, Springer Verlag, Volume 545, p.47-55 (2019)
ISBN : 9789811358012
Keywords : Comparative analysis, Comprehension models, Comprehension tasks, Data handling, Deep learning, Learning techniques, Long short-term memory, NAtural language processing, Natural language processing systems, Natural languages, Neural network model, Question Answering
Campus : Coimbatore
School : School of Engineering
Center : Computational Engineering and Networking
Department : Electronics and Communication
Year : 2019
Abstract : Machine comprehension deals with the idea of teaching machines the ability to read a passage and provide the correct answer to a question asked from it. Creation of machines with the ability to understand natural language is the prime aim of natural language processing. A machine comprehension task is an extension of question answering technique which provides the machines an ability to answer questions. This task revolutionizes the way in which humans interact with machines and retrieve information from them. Recent works in the field of natural language processing reveal the dominance of deep learning technique in handling complex tasks which suggest the use of neural network models for solving machine comprehension tasks. This paper discusses the performance of code-mixed Hindi data for handling machine comprehension using long short-term memory network and gated recurrent unit. A comparative analysis on the basis of accuracy is performed between the two sequence models to determine the best-suited model for handling this task. © 2019, Springer Nature Singapore Pte Ltd.
Cite this Research Publication : S. Viswanathan, M. Kumar, A., and Dr. Soman K. P., “A Sequence-Based Machine Comprehension Modeling Using LSTM and GRU”, in Lecture Notes in Electrical Engineering, 2019, vol. 545, pp. 47-55.