|C|=1000 and Other Brown Clustering Fallacies

Description

Brown clustering has recently re-emerged as a competitive, unsupervised method for learning distributional word representations from an input corpus. It applies a greedy heuristic based on mutual information to group words into clusters, thereby reducing the sparsity of bigram information. Using the clusters as features has been shown over again to incur excellent performance on downstream NLP tasks. In this talk, however, I expose the naivety in how features are currently generated from Brown clusters. With a look into hyperparameter selection, the reality of Brown clustering output, and the algorithm itself, I will show that the space for improving the resultant word representations is predominantly unexplored.

Period	29 Sept 2015
Event title	|C|=1000 and Other Brown Clustering Fallacies
Event type	Seminar
Location	Sheffield, United KingdomShow on map