Eunice Kennedy Shriver Center; Department of Family Medicine and Community Health
Artificial Intelligence and Robotics | Cognitive Neuroscience | Graphics and Human Computer Interfaces
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.
Text Simplification, Recurrent Neural Network, Deep Learning, Natural Language Processing, Machine Translation
Rights and Permissions
Copyright 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Publisher PDF posted as allowed by the publisher’s author copyright policy at https://www.aaai.org/ocs/index.php/AAAI/AAAI16/rt/metadata/11944/0.
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
AAAI’16 Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence
Wang T, Chen P, Rochford J, Qiang J. (2016). Text Simplification Using Neural Machine Translation. Eunice Kennedy Shriver Center Publications. Retrieved from https://escholarship.umassmed.edu/shriver_pp/69