Command Palette
Search for a command to run...
Ruining He Anirudh Ravula Bhargav Kanagal Joshua Ainslie
Abstract
Transformer is the backbone of modern NLP models. In this paper, we propose RealFormer, a simple and generic technique to create Residual Attention Layer Transformer networks that significantly outperform the canonical Transformer and its variants (BERT, ETC, etc.) on a wide spectrum of tasks including Masked Language Modeling, GLUE, SQuAD, Neural Machine Translation, WikiHop, HotpotQA, Natural Questions, and OpenKP. We also observe empirically that RealFormer stabilizes training and leads to models with sparser attention. Source code and pre-trained checkpoints for RealFormer can be found at https://github.com/google-research/google-research/tree/master/realformer.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| linguistic-acceptability-on-cola | RealFormer | Accuracy: 59.83% |
| natural-language-inference-on-multinli | RealFormer | Matched: 86.28 Mismatched: 86.34 |
| natural-language-inference-on-qnli | RealFormer | Accuracy: 91.89% |
| natural-language-inference-on-rte | RealFormer | Accuracy: 73.7% |
| paraphrase-identification-on-quora-question | RealFormer | Accuracy: 91.34 F1: 88.28 |
| semantic-textual-similarity-on-mrpc | RealFormer | Accuracy: 87.01% F1: 90.91% |
| semantic-textual-similarity-on-sts-benchmark | RealFormer | Pearson Correlation: 0.9011 Spearman Correlation: 0.8988 |
| sentiment-analysis-on-sst-2-binary | RealFormer | Accuracy: 94.04 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.