Dependency Recurrent Neural Language Models for Sentence Completion

Recent work on language modelling has shifted focus from count-based models to neural models. In these works, the words in each sentence are always considered in a left-to-right order. In this paper we show how we can improve the performance of the recurrent neural network (RNN) lan- guage model by incorporating the syntac- tic dependencies of a sentence, which have the effect of bringing relevant contexts closer to the word being predicted. We evaluate our approach on the Microsoft Research Sentence Completion Challenge and show that the dependency RNN pro- posed improves over the RNN by about 10 points in accuracy. Furthermore, we achieve results comparable with the state- of-the-art models on this task.