Commonsense Knowledge Enhanced Memory Network for Stance Classification

Stance classification aims at identifying, in the text, the attitude toward the given targets as favorable, negative, or unrelated. In existing models for stance classification, only textual representation is leveraged, while commonsense knowledge is ignored. In order to better incorporate commonsense knowledge into stance classification, we propose a novel model named commonsense knowledge enhanced memory network, which jointly represents textual and commonsense knowledge representation of given target and text. The textual memory module in our model treats the textual representation as memory vectors, and uses attention mechanism to embody the important parts. For commonsense knowledge memory module, we jointly leverage the entity and relation embeddings learned by TransE model to take full advantage of constraints of the knowledge graph. Experimental results on the SemEval dataset show that the combination of the commonsense knowledge memory and textual memory can improve stance classification.

Authors

• Jiachen Du Harbin Institute of Tehnology
• Lin Gui King's College London
• Ruifeng Xu Harbin Institute of Technology, Shenzhen, China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Shenzhen, China Peng Cheng Laboratory, Shenzhen, China
• Yunqing Xia
• Xuan Wang School of Computer Science and Technology, Harbin Institute of Technology Shenzhen

Keywords

• Memory modules
• Knowledge engineering
• Task analysis
• Sentiment analysis
• Predictive models
• Visualization
• Affective computing
• Knowledge representation
• Memory Network
• Commonsense Knowledge
• Stance Classification
• Attention Mechanism
• Text Words
• Word Embedding
• Free Base
• Abortion Law
• Text Representation
• Pseudowords
• Prediction Of Cases
• Natural Language Processing Tasks
• Memory Module
• Knowledge Space
• Common Feature Space
• DBpedia
• Convolutional Neural Network
• Support Vector Machine
• Long Short-term Memory
• Bidirectional Recurrent Network
• Visual Question Answering
• Text Encoder
• Hidden State
• Recurrent Neural Network
• Attention Scores
• Memory Representations
• Final Metric
• Representation For Classification