Direct Output Connection for a High-Rank Language Model
Abstract
This paper proposes a state-of-the-art recurrent neural network (RNN) language model that combines probability distributions computed not only from a final RNN layer but also from middle layers. Our proposed method raises the expressive power of a language model based on the matrix factorization interpretation of language modeling introduced by Yang et al. (2018). The proposed method improves the current state-of-the-art language model and achieves the best score on the Penn Treebank and WikiText-2, which are the standard benchmark datasets. Moreover, we indicate our proposed method contributes to two application tasks: machine translation and headline generation. Our code is publicly available at: https://github.com/nttcslab-nlp/doc_lm.
Cite
@article{arxiv.1808.10143,
title = {Direct Output Connection for a High-Rank Language Model},
author = {Sho Takase and Jun Suzuki and Masaaki Nagata},
journal= {arXiv preprint arXiv:1808.10143},
year = {2018}
}
Comments
EMNLP 2018 paper