Learning Word Embeddings via Context Grouping

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Title of host publicationACM TUR-C '17 : Proceedings of the ACM Turing 50th Celebration Conference - China
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Pages1-10
ISBN (print)9781450348737
Publication statusPublished - 12 May 2017

Publication series

NameACM International Conference Proceeding Series
VolumeF127754

Conference

Title50th ACM Turing Conference - China, ACM TUR-C 2017
PlaceChina
CityShanghai
Period12 - 14 May 2017

Abstract

Recently, neural-network based word embedding models have been shown to produce high-quality distributional representations capturing both semantic and syntactic information. In this paper, we propose a grouping-based context predictive model by considering the interactions of contextwords, which generalizes the widely used CBOWmodel and Skip-Gram model. In particular, the words within a context window are split into several groups with a grouping function, where words in the same group are combined while different groups are treated as independent. To determine the grouping function, we propose a relatedness hypothesis stating the relationship among context words and propose several context grouping methods. Experimental results demonstrate better representations can be learned with suitable context groups.

Research Area(s)

  • Context grouping, Non-parametric clustering, Word embeddings

Citation Format(s)

Learning Word Embeddings via Context Grouping. / Ma, Yun; Li, Qing; Yang, Zhenguo et al.
ACM TUR-C '17 : Proceedings of the ACM Turing 50th Celebration Conference - China. New York: Association for Computing Machinery (ACM), 2017. p. 1-10 24 (ACM International Conference Proceeding Series; Vol. F127754).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review