Accelerated High-Quality Mutual-Information Based Word Clustering

Manuel R Ciosici, Ira Assent, Leon Derczynski

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

Word clustering groups words that exhibit similar properties. One popular method for this is Brown clustering, which uses short-range distributional information to construct clusters. Specifically, this is a hard hierarchical clustering with a fixed-width beam that employs bi-grams and greedily minimizes global mutual information loss. The result is word clusters that tend to outperform or complement other word representations, especially when constrained by small datasets. However, Brown clustering has high computational complexity and does not lend itself to parallel computation. This, together with the lack of efficient implementations, limits their applicability in NLP. We present efficient implementations of Brown clustering and the alternative Exchange clustering as well as a number of methods to accelerate the computation of both hierarchical and flat clusters. We show empirically that clusters obtained with the accelerated method match the performance of clusters computed using the original methods.
OriginalsprogEngelsk
TitelProceedings of The 12th Language Resources and Evaluation Conference
Antal sider6
UdgivelsesstedMarseille, France
ForlagEuropean Language Resources Association
Publikationsdato1 maj 2020
Sider2484-2489
StatusUdgivet - 1 maj 2020

Emneord

  • Word clustering
  • Brown clustering
  • Hierarchical clustering
  • Mutual information
  • Computational complexity

Fingeraftryk

Dyk ned i forskningsemnerne om 'Accelerated High-Quality Mutual-Information Based Word Clustering'. Sammen danner de et unikt fingeraftryk.

Citationsformater