Larger-Context Language Modelling

In this work, we propose a novel method to incorporate corpus-level discourse information into language modelling. We call this larger-context language model. We introduce a late fusion approach to a recurrent language model based on long short-term memory units (LSTM), which helps the LSTM unit keep intra-sentence dependencies and inter-sentence dependencies separate from each other. Through the evaluation on three corpora (IMDB, BBC, and PennTree Bank), we demonstrate that the proposed model improves perplexity significantly. In the experiments, we evaluate the proposed approach while varying the number of context sentences and observe that the proposed late fusion is superior to the usual way of incorporating additional inputs to the LSTM. By analyzing the trained largercontext language model, we discover that content words, including nouns, adjectives and verbs, benefit most from an increasing number of context sentences. This analysis suggests that larger-context language model improves the unconditional language model by capturing the theme of a document better and more easily.