GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method
Abstract
Large pre-trained language models such as BERT have been the driving force behind recent improvements across many NLP tasks. However, BERT is only trained to predict missing words - either behind masks or in the next sentence - and has no knowledge of lexical, syntactic or semantic information beyond what it picks up through unsupervised pre-training. We propose a novel method to explicitly inject linguistic knowledge in the form of word embeddings into any layer of a pre-trained BERT. Our performance improvements on multiple semantic similarity datasets when injecting dependency-based and counter-fitted embeddings indicate that such information is beneficial and currently missing from the original model. Our qualitative analysis shows that counter-fitted embedding injection particularly helps with cases involving synonym pairs.
Cite
@article{arxiv.2010.12532,
title = {GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method},
author = {Nicole Peinelt and Marek Rei and Maria Liakata},
journal= {arXiv preprint arXiv:2010.12532},
year = {2020}
}