Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach
This addresses the problem of improving language modeling efficiency for NLP researchers, but it is incremental as it builds on existing multi-task approaches.
The paper tackles the challenge of incorporating syntactic structure into neural language models by using a multi-task objective that predicts words and parse trees as syntactic distances, resulting in lower perplexity and better tree quality on Penn Treebank and Chinese Treebank datasets.
It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic. In this paper, we make use of a multi-task objective, i.e., the models simultaneously predict words as well as ground truth parse trees in a form called "syntactic distances", where information between these two separate objectives shares the same intermediate representation. Experimental results on the Penn Treebank and Chinese Treebank datasets show that when ground truth parse trees are provided as additional training signals, the model is able to achieve lower perplexity and induce trees with better quality.