Malayalam Question Answering System Using Deep Learning Approaches

ABSTRACT

Question Answering (QA) systems attempt to retrieve precise answers to questions posed in natural language by the users. It is a sophisticated form of Information Retrieval (IR) that uses a predefined collection of raw data in natural language. Malayalam is an official language in India, that is not only morphologically rich and agglutinative in nature but is also resource constrained. These aspects of the language make QA in Malayalam very challenging. This paper proposes a deep learning based QA system for Malayalam using techniques such as Long Short-Term Memory Networks (LSTM), Gated Recurrent Unit (GRU), and Memory Network models. Facebook bAbI dataset consisting of 20 tasks with the questions having multiple supporting facts, inductive and deductive reasoning, coreference, etc. have been used to train and test the system. It was observed that the Memory Network model achieved the best average accuracy (80%) among the three models implemented, in retrieving exact answers in Malayalam. This work is unique because all the reported work on Malayalam QA is rule-based, capable of extracting answers to factoid questions only. The proposed system which uses deep learning approaches is scalable and thus capable of enhancing the ongoing research in Malayalam QA along with the development of the Malayalam QA corpus.

KEYWORDS:

• Deep learning
• Gated Recurrent Unit
• Long Short-Term Memory Networks
• Memory Networks
• Natural Language Processing
• Neural networks
• Question answering

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Reji Rahmath K

Reji Rahmath K is a PhD scholar at APJ Abdul Kalam Technological University, Kerala, India. She received her BTech and MTech degrees from Calicut University. She is currently pursuing research in the area of computational linguistics. Her specific research direction is to implement question answering system in Malayalam using machine learning algorithms.

P.C. Reghu Raj

P C Reghu Raj received his BTech degree in computer engineering from REC Calicut, MTech in computer and information sciences from CUSAT Cochin, and PhD from IIT Madras. He is currently an academician in APJ Abdul Kalam Technological University, Kerala. His area of research includes computational linguistics and information retrieval. He has more than 60 publications in refereed international journals,  international and national conferences. Email: [email protected]

Rafeeque P C

Rafeeque P C received his BTech from Calicut University, MTech in computer science and engineering from NIT Calicut and PhD from Anna University, Chennai. He is currently a teaching faculty in APJ Abdul Kalam Technological University. His research interests are mainly in the areas of data mining and machine learning. He has more than 20 publications in refereed journals,  international and national conferences. Email: [email protected]