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 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.- Anthology ID:
- 2021.findings-emnlp.200
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2322–2336
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.200
- DOI:
- 10.18653/v1/2021.findings-emnlp.200
- Cite (ACL):
- Nicole Peinelt, Marek Rei, and Maria Liakata. 2021. GiBERT: Enhancing BERT with Linguistic Information using a Lightweight Gated Injection Method. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2322–2336, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- GiBERT: Enhancing BERT with Linguistic Information using a Lightweight Gated Injection Method (Peinelt et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.findings-emnlp.200.pdf
- Code
- wuningxi/gibert