Question classification is a key task in many question answering applications. Nearly all previous work on question classification has used machine learning and knowledge-based methods. This working note presents an embedding based Bag-of-Words method and Recurrent Neural Network to achieve an automatic question classification in the code-mixed Bengali-English text. We build two systems that classify questions mostly at the sentence level. We used a recurrent neural network for extracting features from the questions and Logistic regression for classification. We conduct experiments on Mixed Script Information Retrieval (MSIR) Task 1 dataset at FIRE20161. The experimental result shows that the proposed method is appropriate for the question classification task.
cited By 0; Conference of 2016 Forum for Information Retrieval Evaluation, FIRE 2016 ; Conference Date: 7 December 2016 Through 10 December 2016; Conference Code:125007
Dr. M. Anand Kumar, Dr. Soman K. P., and Dr. Soman K. P., “Amrita-CEN@MSIR-FIRE2016: Code-mixed question classification using BoWs and RNN Embeddings”, in CEUR Workshop Proceedings, 2016, vol. 1737, pp. 122-125.