Dependency Recurrent Neural Language Models for Sentence Completion

TL;DR

This paper enhances neural language models by integrating syntactic dependencies, improving sentence completion accuracy and achieving state-of-the-art results on a benchmark dataset.

Contribution

It introduces a dependency-based recurrent neural network that incorporates syntactic structures to improve language modeling performance.

Findings

Dependency RNN improves accuracy by about 10 points.

Achieves results comparable to state-of-the-art models.

Demonstrates the effectiveness of syntactic dependencies in language models.

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 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.