SHED CLASSING VERSUS STORE CLASSING

Enhanced word classing for model M

Model M is a superior class-based n-gram model that has shown improvements on a variety of tasks and domains. In previous work with Model M, bigram mutual information clustering has been used to derive word classes. In this paper, we introduce a new word classing method designed to closely match with Model M. The proposed classing technique achieves gains in speech recognition word-error rate o...

Soft-Classing to Create Evolving Ontologies for Distributed Resources

The value of a distributed resource is often enhanced by its remaining distributed and under the control of the party responsible for its creation and maintenance. Metadata expressed as XML provides a mechanism to publish the existence of this resource and to support multiple access of the resource from its source location. In this way, uncertainty is minimized about whether the resource is cur...

A Study of Word-Classing for MT Reordering

MT systems typically use parsers to help reorder constituents. However most languages do not have adequate treebank data to learn good parsers, and such training data is extremely time-consuming to annotate. Our earlier work has shown that a reordering model learnt from word-alignments using POS tags as features can improve MT performance (Visweswariah et al., 2011). In this paper, we investiga...

Enhanced Word Classing for Recurrent Neural Network Language

Recurrent Neural Network Language Model (RNNLM) has recently been shown to outperform conventional N-gram LM as well as many other competing advanced language model techniques. However, the computation complexity of RNNLM is much higher than the conventional N-gram LM. As a result, the Class-based RNNLM (CRNNLM) is usually employed to speed up both the training and testing phase of RNNLM. In pr...

Classing Ethnicity: Class, Ethnicity and the Mass Politics of Taiwan’s Democratic Transition