Two layers LSTM with attention for multi-choice question answering in exams

International Conference on Functional Materials and Chemical Engineering 2017

材料科学;化学工业

Li, Yongbin^1,2

ZunYi Medical University, No.6 Xuefu West Road, Xinpu new distract, Zunyi, GuiZhou, China^1

YunNan University, Chenggong Distract, University City, Kunming, Yun, China^2

关键词: Attention model;    CNN models;    Extracting features;    Learning models;    Multi choices;    Question Answering;    Question Answering Task;    Word embedding;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/323/1/012023/pdf
DOI  :  10.1088/1757-899X/323/1/012023

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

Question Answering in Exams is typical question answering task that aims to test how accurately the model could answer the questions in exams. In this paper, we use general deep learning model to solve the multi-choice question answering task. Our approach is to build distributed word embedding of question and answers instead of manually extracting features or linguistic tools, meanwhile, for improving the accuracy, the external corpus is introduced. The framework uses a two layers LSTM with attention which get a significant result. By contrast, we introduce the simple long short-term memory (QA-LSTM) model and QA-LSTM-CNN model and QA-LSTM with attention model as the reference. Experiment demonstrate superior performance of two layers LSTM with attention compared to other models in question answering task.