Accelerated High-Quality Mutual-Information Based Word Clustering
Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review
Standard
Accelerated High-Quality Mutual-Information Based Word Clustering. / Ciosici, Manuel R; Assent, Ira; Derczynski, Leon.
Proceedings of The 12th Language Resources and Evaluation Conference. Marseille, France : European Language Resources Association, 2020. p. 2484-2489.Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Accelerated High-Quality Mutual-Information Based Word Clustering
AU - Ciosici, Manuel R
AU - Assent, Ira
AU - Derczynski, Leon
PY - 2020/5/1
Y1 - 2020/5/1
N2 - 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.
AB - 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.
M3 - Article in proceedings
SP - 2484
EP - 2489
BT - Proceedings of The 12th Language Resources and Evaluation Conference
PB - European Language Resources Association
CY - Marseille, France
ER -
ID: 85114970