Question Classification on Question-Answer System using Bidirectional-LSTM

The first step in the question-answer system is question analysis. This step was carried out with various processes, one of them was question classification. The question classification process can determine the accuracy of the answers generated by the system. Some approaches that have been used are Support Vector Machine (SVM), pattern matching, naïve bayes classification and Latent Dirichlet Allocation (LDA). Research on question classification using that approach has been widely carried out but still only work on certain sentence patterns. These problems can be solved using deep learning method, one of them is Bidirectional Long Short Term Memory (Bi-LSTM). Bi-LSTM does not depend on certain sentence patterns. Bi-LSTM has good accuracy in text classification. This study uses Bi-LSTM in the question classification process. Questions divided into three classes, that is greeting, daily conversation, and meetings. The classification results show the accuracy of 0.909 with loss of 0.316. Bi-LSTM has higher accuracy compared to basic LSTM and Recurrent Neural Network (RNN). Based on the results, Bi-LSTM can be used as question classification method for Question Answer System (QA System).

[1]  Alaa Mohasseb,et al.  Question categorization and classification using grammar based approach , 2018, Inf. Process. Manag..

[2]  Fajri Koto.  A Publicly Available Indonesian Corpora for Automatic Abstractive and Extractive Chat Summarization , 2016, LREC.

[3]  Bhadrachalam Chitturi,et al.  Deep learning model on stance classification , 2017, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[4]  Swati Pathak,et al.  Context aware restricted tourism domain question answering system , 2016, 2016 2nd International Conference on Next Generation Computing Technologies (NGCT).

[5]  Khaled Shaalan,et al.  Semantic Based Query Expansion for Arabic Question Answering Systems , 2015, 2015 First International Conference on Arabic Computational Linguistics (ACLing).

[6]  Saeedeh Momtazi,et al.  Unsupervised Latent Dirichlet Allocation for supervised question classification , 2018, Inf. Process. Manag..

[7]  Md. Saiful Islam,et al.  Question classification using support vector machine with hybrid feature extraction method , 2017, 2017 20th International Conference of Computer and Information Technology (ICCIT).

[8]  Wiwin Suwarningsih,et al.  Indonesian medical question classification with pattern matching , 2015, 2015 International Conference on Automation, Cognitive Science, Optics, Micro Electro-Mechanical System, and Information Technology (ICACOMIT).

[9]  Ferry Wahyu Wibowo,et al.  Chatbot Using a Knowledge in Database: Human-to-Machine Conversation Modeling , 2016, 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS).

[10]  Dietrich Klakow,et al.  Linguistically Motivated Question Classification , 2015, NODALIDA.

[11]  Surangika Ranathunga,et al.  Question Answering system for the travel domain , 2017, 2017 Moratuwa Engineering Research Conference (MERCon).

[12]  Sanket Thakare,et al.  Real world smart chatbot for customer care using a software as a service (SaaS) architecture , 2017, 2017 International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC).

[13]  Pinar Senkul,et al.  Movie Genre Classification from Plot Summaries Using Bidirectional LSTM , 2018, 2018 IEEE 12th International Conference on Semantic Computing (ICSC).

[14]  Zhiyong Feng,et al.  LSTM with sentence representations for document-level sentiment classification , 2018, Neurocomputing.