# Confidence-Aware Scheduled Sampling for Neural Machine Translation

arXiv: https://arxiv.org/abs/2107.10427 · HTML: https://mlsanity.com/paper/2107.10427/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 22 Jul 2021.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Learning Deep Transformer Models for Machine Translation](https://mlsanity.com/paper/1906.01787/) (2019)
- [Analyzing Uncertainty in Neural Machine Translation](https://mlsanity.com/paper/1803.00047/) (2018)
- [Bridging the Gap between Training and Inference for Neural Machine Translation](https://mlsanity.com/paper/1906.02448/) (2019)
- [Minimum Risk Training for Neural Machine Translation](https://mlsanity.com/paper/1512.02433/) (2015)
- [Calibration of Encoder Decoder Models for Neural Machine Translation](https://mlsanity.com/paper/1903.00802/) (2019)
- [On the Inference Calibration of Neural Machine Translation](https://mlsanity.com/paper/2005.00963/) (2020)
- [Scheduled Sampling for Transformers](https://mlsanity.com/paper/1906.07651/) (2019)
- [No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling](https://mlsanity.com/paper/1804.09160/) (2018)
- [Improving Back-Translation with Uncertainty-based Confidence Estimation](https://mlsanity.com/paper/1909.00157/) (2019)
- [Synchronous Bidirectional Neural Machine Translation](https://mlsanity.com/paper/1905.04847/) (2019)
- [Self-Paced Learning for Neural Machine Translation](https://mlsanity.com/paper/2010.04505/) (2020)
- [Dynamic Data Selection and Weighting for Iterative Back-Translation](https://mlsanity.com/paper/2004.03672/) (2020)
- [Parallel Scheduled Sampling](https://mlsanity.com/paper/1906.04331/) (2019)
- [Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation](https://mlsanity.com/paper/2010.02552/) (2020)
- [Differentiable Scheduled Sampling for Credit Assignment](https://mlsanity.com/paper/1704.06970/) (2017)
- [Uncertainty-Aware Semantic Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2010.04411/) (2020)
- [WeChat Neural Machine Translation Systems for WMT20](https://mlsanity.com/paper/2010.00247/) (2020)
- [Synchronous Bidirectional Inference for Neural Sequence Generation](https://mlsanity.com/paper/1902.08955/) (2019)
- [TeaForN: Teacher-Forcing with N-grams](https://mlsanity.com/paper/2010.03494/) (2020)
- [Hard but Robust, Easy but Sensitive: How Encoder and Decoder Perform in Neural Machine Translation](https://mlsanity.com/paper/1908.06259/) (2019)

## Built on by (most cited first, 10 of 10)

- [WeChat Neural Machine Translation Systems for WMT21](https://mlsanity.com/paper/2108.02401/) (2021)
- [Scheduled Sampling Based on Decoding Steps for Neural Machine Translation](https://mlsanity.com/paper/2108.12963/) (2021)
- [Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation](https://mlsanity.com/paper/2305.08096/) (2023)
- [Auto-regressive Image Synthesis with Integrated Quantization](https://mlsanity.com/paper/2207.10776/) (2022)
- [Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation](https://mlsanity.com/paper/2203.02951/) (2022)
- [CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training](https://mlsanity.com/paper/2311.03672/) (2023)
- [Towards Robust Online Dialogue Response Generation](https://mlsanity.com/paper/2203.03168/) (2022)
- [Dynamic Scheduled Sampling with Imitation Loss for Neural Text Generation](https://mlsanity.com/paper/2301.13753/) (2023)
- [Bilevel Scheduled Sampling for Dialogue Generation](https://mlsanity.com/paper/2309.01953/) (2023)
- [AUGlasses: Continuous Action Unit based Facial Reconstruction with Low-power IMUs on Smart Glasses](https://mlsanity.com/paper/2405.13289/) (2024)

## Abstract (arXiv)

Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth target input tokens with predicted ones during training. Despite its success, its critical schedule strategies are merely based on training steps, ignoring the real-time model competence, which limits its potential performance and convergence speed. To address this issue, we propose confidence-aware scheduled sampling. Specifically, we quantify real-time model competence by the confidence of model predictions, based on which we design fine-grained schedule strategies. In this way, the model is exactly exposed to predicted tokens for high-confidence positions and still ground-truth tokens for low-confidence positions. Moreover, we observe vanilla scheduled sampling suffers from degenerating into the original teacher forcing mode since most predicted tokens are the same as ground-truth tokens. Therefore, under the above confidence-aware strategy, we further expose more noisy tokens (e.g., wordy and incorrect word order) instead of predicted ones for high-confidence token positions. We evaluate our approach on the Transformer and conduct experiments on large-scale WMT 2014 English-German, WMT 2014 English-French, and WMT 2019 Chinese-English. Results show that our approach significantly outperforms the Transformer and vanilla scheduled sampling on both translation quality and convergence speed.