Predicting syntactic information in a joint language model (LM) has been shown not only to improve the model at its main task of predicting words, but it also allows this information to be passed to other applications, such as spoken language processing. This raises the question of just how accurate the syntactic information predicted by the LM is. In this paper, we present a joint LM designed not only to scale to large quantities of training data, but also to be able to utilize fine-grain syntactic information, as well as other features, such as morphology and prosody. We evaluate the accuracy of our model at predicting syntactic information on the POS tagging task against state-of-the-art POS taggers and on perplexity against the ngram model.
Bibliographic reference. Filimonov, Denis / Harper, Mary (2009): "Measuring tagging performance of a joint language model", In INTERSPEECH-2009, 2667-2670.