# BERTVision -- A Parameter-Efficient Approach for Question Answering

arXiv: https://arxiv.org/abs/2202.12210 · HTML: https://mlsanity.com/paper/2202.12210/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 15 references that are in the map.
- First posted on arXiv 24 Feb 2022.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [Universal Text Representation from BERT: An Empirical Study](https://mlsanity.com/paper/1910.07973/) (2019)
- [Table Search Using a Deep Contextualized Language Model](https://mlsanity.com/paper/2005.09207/) (2020)

## Built on by (most cited first, 1 of 1)

- [Vision HgNN: An Electron-Micrograph is Worth Hypergraph of Hypernodes](https://mlsanity.com/paper/2408.11351/) (2024)

## Abstract (arXiv)

We present a highly parameter efficient approach for Question Answering that significantly reduces the need for extended BERT fine-tuning. Our method uses information from the hidden state activations of each BERT transformer layer, which is discarded during typical BERT inference. Our best model achieves maximal BERT performance at a fraction of the training time and GPU or TPU expense. Performance is further improved by ensembling our model with BERTs predictions. Furthermore, we find that near optimal performance can be achieved for QA span annotation using less training data. Our experiments show that this approach works well not only for span annotation, but also for classification, suggesting that it may be extensible to a wider range of tasks.