TL;DR本文研究了如何将RNN语言模型与句子的句法依赖相结合，以提高递归神经网络(RNN)语言模型的性能和准确率，并在Microsoft Research Sentence Completion Challenge的评估中展示了其优越性，并达到了同类最先进模型的效果。
Abstract
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 w