A Tensorized Transformer for Language Modeling
Abstract
Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP) tasks. However, the multi-head attention mechanism, as a key component of Transformer, limits the effective deployment of the model to a resource-limited setting. In this paper, based on the ideas of tensor decomposition and parameters sharing, we propose a novel self-attention model (namely Multi-linear attention) with Block-Term Tensor Decomposition (BTD). We test and verify the proposed attention method on three language modeling tasks (i.e., PTB, WikiText-103 and One-billion) and a neural machine translation task (i.e., WMT-2016 English-German). Multi-linear attention can not only largely compress the model parameters but also obtain performance improvements, compared with a number of language modeling approaches, such as Transformer, Transformer-XL, and Transformer with tensor train decomposition.
Cite
@article{arxiv.1906.09777,
title = {A Tensorized Transformer for Language Modeling},
author = {Xindian Ma and Peng Zhang and Shuai Zhang and Nan Duan and Yuexian Hou and Dawei Song and Ming Zhou},
journal= {arXiv preprint arXiv:1906.09777},
year = {2019}
}
Comments
Accepted by NeurIPS 2019