A Generalized Language Model in Tensor Space
Abstract
In the literature, tensors have been effectively used for capturing the context information in language models. However, the existing methods usually adopt relatively-low order tensors, which have limited expressive power in modeling language. Developing a higher-order tensor representation is challenging, in terms of deriving an effective solution and showing its generality. In this paper, we propose a language model named Tensor Space Language Model (TSLM), by utilizing tensor networks and tensor decomposition. In TSLM, we build a high-dimensional semantic space constructed by the tensor product of word vectors. Theoretically, we prove that such tensor representation is a generalization of the n-gram language model. We further show that this high-order tensor representation can be decomposed to a recursive calculation of conditional probability for language modeling. The experimental results on Penn Tree Bank (PTB) dataset and WikiText benchmark demonstrate the effectiveness of TSLM.
Cite
@article{arxiv.1901.11167,
title = {A Generalized Language Model in Tensor Space},
author = {Lipeng Zhang and Peng Zhang and Xindian Ma and Shuqin Gu and Zhan Su and Dawei Song},
journal= {arXiv preprint arXiv:1901.11167},
year = {2019}
}