Annealing Techniques For Unsupervised Statistical Language Learning

Exploiting unannotated natural language data is hard largely because unsupervised parameter estimation is hard. We describe deterministic annealing (Rose et al., 1990) as an appealing alternative to the ExpectationMaximization algorithm (Dempster et al., 1977). Seeking to avoid search error, DA begins by globally maximizing an easy concave function and maintains a local maximum as it gradually morphs the function into the desired non-concave likelihood function. Applying DA to parsing and tagging models is shown to be straightforward; significant improvements over EM are shown on a part-of-speech tagging task. We describe a variant, skewed DA, which can incorporate a good initializer when it is available, and show significant improvements over EM on a grammar induction task.