Language Modeling Using Tensor Trains
Abstract
We propose a novel tensor network language model based on the simplest tensor network (i.e., tensor trains), called `Tensor Train Language Model' (TTLM). TTLM represents sentences in an exponential space constructed by the tensor product of words, but computing the probabilities of sentences in a low-dimensional fashion. We demonstrate that the architectures of Second-order RNNs, Recurrent Arithmetic Circuits (RACs), and Multiplicative Integration RNNs are, essentially, special cases of TTLM. Experimental evaluations on real language modeling tasks show that the proposed variants of TTLM (i.e., TTLM-Large and TTLM-Tiny) outperform the vanilla Recurrent Neural Networks (RNNs) with low-scale of hidden units. (The code is available at https://github.com/shuishen112/tensortrainlm.)
Cite
@article{arxiv.2405.04590,
title = {Language Modeling Using Tensor Trains},
author = {Zhan Su and Yuqin Zhou and Fengran Mo and Jakob Grue Simonsen},
journal= {arXiv preprint arXiv:2405.04590},
year = {2024}
}