We present power low rank ensembles (PLRE), a flexible framework for n-gram language modeling where ensembles of low rank matrices and tensors are used to obtain smoothed probability estimates of words in context. Our method can be understood as a generalization of n-gram modeling to non-integer n, and includes standard techniques such as absolute discounting and Kneser-Ney smoothing as special cases. PLRE training is efficient and our approach outperforms state-of-the-art modified Kneser Ney baselines in terms of perplexity on large corpora as well as on BLEU score in a downstream machine translation task.
@article{arxiv.1312.7077,
title = {Language Modeling with Power Low Rank Ensembles},
author = {Ankur P. Parikh and Avneesh Saluja and Chris Dyer and Eric P. Xing},
journal= {arXiv preprint arXiv:1312.7077},
year = {2014}
}