Abstract
The task of Question Answering is at the very core of machine comprehension. In this paper, we propose a Convolutional Neural Network (CNN) model for text-based multiple choice question answering where questions are based on a particular article. Given an article and a multiple choice question, our model assigns a score to each question-option tuple and chooses the final option accordingly. We test our model on Textbook Question Answering (TQA) and SciQ dataset. Our model outperforms several LSTM-based baseline models on the two datasets.- Anthology ID:
- P18-2044
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 272–277
- Language:
- URL:
- https://aclanthology.org/P18-2044
- DOI:
- 10.18653/v1/P18-2044
- Cite (ACL):
- Akshay Chaturvedi, Onkar Pandit, and Utpal Garain. 2018. CNN for Text-Based Multiple Choice Question Answering. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 272–277, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- CNN for Text-Based Multiple Choice Question Answering (Chaturvedi et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/P18-2044.pdf
- Code
- akshay107/CNN-QA
- Data
- SciQ, TQA