We present new training methods that aim to mitigate local optima and slow convergence in unsupervised training by using additional imperfect objectives. In its simplest form, lat...
Valentin I. Spitkovsky, Hiyan Alshawi, Daniel Jura...
We present a novel approach to distributionalonly, fully unsupervised, POS tagging, based on an adaptation of the EM algorithm for the estimation of a Gaussian mixture. In this ap...
Exploiting unannotated natural language data is hard largely because unsupervised parameter estimation is hard. We describe deterministic annealing (Rose et al., 1990) as an appea...
This paper explores the use of two graph algorithms for unsupervised induction and tagging of nominal word senses based on corpora. Our main contribution is the optimization of th...
We show how web mark-up can be used to improve unsupervised dependency parsing. Starting from raw bracketings of four common HTML tags (anchors, bold, italics and underlines), we ...
Valentin I. Spitkovsky, Daniel Jurafsky, Hiyan Als...