Skip to main navigation Skip to search Skip to main content

WINGS: Writing with intelligent guidance and suggestions

  • School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationACL 2014 - 52nd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Student Research Workshop
EditorsEkaterina Kochmar, Kalina Bontcheva, Annie Louis, Jingbo Zhu, Svitlana Volkova, Jordan Boyd-Graber, Bill Byrne
PublisherAssociation for Computational Linguistics (ACL)
Pages25-30
Number of pages6
ISBN (Electronic)9781937284794, 9781941643006
DOIs
StatePublished - 2014
Externally publishedYes
Event52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States
Duration: 22 Jun 201427 Jun 2014

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume2014-June
ISSN (Print)0736-587X

Conference

Conference52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
Country/TerritoryUnited States
CityBaltimore, MD
Period22/06/1427/06/14

Fingerprint

Dive into the research topics of 'WINGS: Writing with intelligent guidance and suggestions'. Together they form a unique fingerprint.

Cite this