Language Modeling Using Tensor Trains
This work addresses language modeling for NLP applications, presenting an incremental improvement by generalizing existing architectures into a tensor network framework.
The authors tackled language modeling by proposing a tensor train-based model (TTLM) that represents sentences in an exponential space but computes probabilities efficiently, showing that TTLM variants outperform vanilla RNNs with low-scale hidden units in experiments.
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.)