2016 International Conference on Big Data and Smart Computing (BigComp) (2016)
Hong Kong, China
Jan. 18, 2016 to Jan. 20, 2016
Hyun Woo Do , Department of Computer Science, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 305-701, South Korea
Young-Seob Jeong , Department of Computer Science, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 305-701, South Korea
We proposed neural network architecture based on Convolution Neural Network(CNN) for temporal relation classification in sentence. First, we transformed word into vector by using word embedding. In Feature Extraction, we extracted two type of features. Lexical level feature considered meaning of marked entity and Sentence level feature considered context of the sentence. Window processing was used to reflect local context and Convolution and Max-pooling operation were used for global context. We concatenated both feature vectors and used softmax operation to compute confidence score. Because experiment results didn't outperform the state-of-the-art methods, we suggested some future works to do.
Feature extraction, Neural networks, Computer architecture, Convolution, Context, Training, Syntactics
Hyun Woo Do and Y. Jeong, "Temporal relation classification with deep neural network," 2016 International Conference on Big Data and Smart Computing (BigComp)(BIGCOMP), Hong Kong, China, 2016, pp. 454-457.