Special Offer: Get 50% off your first 2 months when you do one of the following
Personalized offer codes will be given in each session

(AIMS 2020) Answer Selection Based on Mixed Embedding and Composite Features

About This Webinar

Abstract: With the rapid growth of text information, intelligent question answering has gained more attention than ever. In this paper, we focus on answer selection, one kind of question answering tasks. In this field, deep neural networks and attention mechanism have brought encouraging results. To improve the performance further, we investigate mixed embedding (word embedding and character embedding) representation for sentences to encode rich meaning. At the same time, we introduce a convolutional neural network (CNN) to compensate the loss of the max pooling layer in our attention based bidirectional Long Short-Term Memory (biLSTM) model. CNN features and the features from max pooling form final composite features, which are employed to select correct answers. Experimental results show that we can obviously improve the Mean Reciprocal Rank (MRR) performance by 6.0% with the help of mixed embedding and composite features. The MRR and ACC@1 score are 79.63% and 69.60% respectively.

Authors: Mingli Wu, Xianwei Cui, Jiale Li and Jianyong Duan (North China University of Technology, China)

Email: wuml@ncut.edu.cn, cuixw1227@163.com, lijiale.korn@gmail.com, duan_jianyong@163.com

Who can view: Everyone
Webinar Price: Free
Featured Presenters
Webinar hosting presenter Services Society
Xianwei Cui, a graduate student, comes from the School of Information, North China University of Technology.
Research Interests: Intelligent Q&A, Natural Language Processing
E-mail: cuixw1227@163.com
Hosted By
Services Society webinar platform hosts (AIMS 2020) Answer Selection Based on Mixed Embedding and Composite Features
Services Society's Channel