Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering

14 Mar 2017  ·  Junbei Zhang, Xiaodan Zhu, Qian Chen, Li-Rong Dai, Si Wei, Hui Jiang ·

The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA). In this paper, we approach the problems by closely modelling questions in a neural network framework. We first introduce syntactic information to help encode questions. We then view and model different types of questions and the information shared among them as an adaptation task and proposed adaptation models for them. On the Stanford Question Answering Dataset (SQuAD), we show that these approaches can help attain better results over a competitive baseline.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering SQuAD1.1 jNet (ensemble) EM 73.010 # 135
F1 81.517 # 136
Question Answering SQuAD1.1 jNet (single model) EM 70.607 # 156
F1 79.821 # 153
Question Answering SQuAD1.1 dev jNet (TreeLSTM adaptation, QTLa, K=100) EM 69.10 # 40
F1 78.38 # 43


No methods listed for this paper. Add relevant methods here