WINGS:Writing with Intelligent Guidance and Suggestions

Without inspirations, writing may be a frustrating task for most people. In this study, we designed and implemented WINGS, a Chinese input method extended on IBus-Pinyin with intelligent writing assistance. In addition to supporting common Chinese input, WINGS mainly attempts to spark users’ inspirations by recommending both word level and sentence level writing suggestions. The main strategies used by WINGS, including providing syntactically and semantically related words based on word vector representation and recommending contextually related sentences based on LDA, are discussed and described. Experimental results suggest that WINGS can facilitate Chinese writing in an effective and creative manner.

[1]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[2]  Zheng Chen,et al.  A New Statistical Approach To Chinese Pinyin Input , 2000, ACL.

[3]  Changning Huang,et al.  PENS: A Machine-aided English Writing System for Chinese Users , 2000, ACL.

[4]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[5]  Chih-Wei Chen,et al.  Computer assisted writing system , 2011, Expert Syst. Appl..

[6]  H. Komatsu,et al.  Corpus-based predictive text input , 2005, Proceedings of the 2005 International Conference on Active Media Technology, 2005. (AMT 2005)..

[7]  Chien-Liang Liu,et al.  Intelligent computer assisted blog writing system , 2012, Expert Syst. Appl..

[8]  Jason S. Chang,et al.  FLOW: A First-Language-Oriented Writing Assistant System , 2012, ACL.