Papers › GiBERT: Enhancing BERT with Linguistic Information using a Lightweight Gated Injection Method

GiBERT: Enhancing BERT with Linguistic Information using a Lightweight Gated Injection Method

1 Nov 2021Findings (EMNLP) 2021 11archive 2025-07-28

Nicole Peinelt, Marek Rei, Maria Liakata

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 through masking or next sentence prediction – 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 information in the form of word embeddings into any layer of a pre-trained BERT. When injecting counter-fitted and dependency-based embeddings, the performance improvements on multiple semantic similarity datasets indicate that such information is beneficial and currently missing from the original model. Our qualitative analysis shows that counter-fitted embedding injection is particularly beneficial, with notable improvements on examples that require synonym resolution.

PaperPDFCode

Code

wuningxi/gibert officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Semantic SimilaritySemantic Textual SimilaritySentenceUnsupervised Pre-trainingWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections