From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables
release_jy4t6fdp3bfsph7y3c6bvrqc4i
by
Krtin Kumar, Peyman Passban, Mehdi Rezagholizadeh, Yiu Sing Lau, Qun Liu
2022
Abstract
Embedding matrices are key components in neural natural language processing
(NLP) models that are responsible to provide numerical representations of input
tokens.[In this paper words and subwords are referred to as
tokens and the term embedding only refers to embeddings of
inputs.] In this paper, we analyze the impact and utility of such matrices in
the context of neural machine translation (NMT). We show that detracting
syntactic and semantic information from word embeddings and running NMT systems
with random embeddings is not as damaging as it initially sounds. We also show
how incorporating only a limited amount of task-specific knowledge from
fully-trained embeddings can boost the performance NMT systems. Our findings
demonstrate that in exchange for negligible deterioration in performance, any
NMT model can be run with partially random embeddings. Working with such
structures means a minimal memory requirement as there is no longer need to
store large embedding tables, which is a significant gain in industrial and
on-device settings. We evaluated our embeddings in translating English into
German and French and achieved a 5.3x compression rate. Despite having a
considerably smaller architecture, our models in some cases are even able to
outperform state-of-the-art baselines.
In text/plain
format
Archived Files and Locations
application/pdf 527.7 kB
file_hdrtpmehkfhnxhen6spo5qyrjq
|
arxiv.org (repository) web.archive.org (webarchive) |
2104.08677v2
access all versions, variants, and formats of this works (eg, pre-prints)