Dependency Recurrent Neural Language Models for Sentence Completion
This work addresses sentence completion tasks for natural language processing, offering an incremental improvement over existing neural models.
The paper tackled the problem of improving recurrent neural network language models by incorporating syntactic dependencies to bring relevant contexts closer to predicted words, resulting in about a 10-point accuracy improvement on the Microsoft Research Sentence Completion Challenge and achieving results comparable to state-of-the-art models.
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) language model by incorporating the syntactic 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 proposed 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.