UMass Chan Affiliations
Department of Family Medicine and Community HealthEunice Kennedy Shriver Center
Document Type
Conference PaperPublication Date
2016-03-05Keywords
Text SimplificationRecurrent Neural Network
Deep Learning
Natural Language Processing
Machine Translation
Artificial Intelligence and Robotics
Cognitive Neuroscience
Graphics and Human Computer Interfaces
Metadata
Show full item recordAbstract
Text simplification (TS) is the technique of reducing the lexical, syntactical complexity of text. Existing automatic TS systems can simplify text only by lexical simplification or by manually defined rules. Neural Machine Translation (NMT) is a recently proposed approach for Machine Translation (MT) that is receiving a lot of research interest. In this paper, we regard original English and simplified English as two languages, and apply a NMT model–Recurrent Neural Network (RNN) encoder-decoder on TS to make the neural network to learn text simplification rules by itself. Then we discuss challenges and strategies about how to apply a NMT model to the task of text simplification.Source
Wang, T., Chen, P., Rochford, J., & Qiang, J. (2016). Text simplification using Neural Machine Translation. In AAAI’16 Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (pp. 4270–7271). Link to publisher website