# Onception: Active Learning with Expert Advice for Real World Machine Translation

arXiv: https://arxiv.org/abs/2203.04507 · HTML: https://mlsanity.com/paper/2203.04507/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 99 references that are in the map.
- First posted on arXiv 9 Mar 2022.

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

- [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)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [Online Learning: A Comprehensive Survey](https://mlsanity.com/paper/1802.02871/) (2018)
- [Facebook FAIR's WMT19 News Translation Task Submission](https://mlsanity.com/paper/1907.06616/) (2019)
- [Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing](https://mlsanity.com/paper/2004.14564/) (2020)
- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [Learning how to Active Learn: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1708.02383/) (2017)
- [Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback](https://mlsanity.com/paper/1707.07402/) (2017)
- [Practical Obstacles to Deploying Active Learning](https://mlsanity.com/paper/1807.04801/) (2018)
- [Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation](https://mlsanity.com/paper/1907.06170/) (2019)
- [ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations](https://mlsanity.com/paper/1711.05732/) (2017)
- [Active Learning for Interactive Neural Machine Translation of Data Streams](https://mlsanity.com/paper/1807.11243/) (2018)
- [The University of Edinburgh's Submissions to the WMT19 News Translation Task](https://mlsanity.com/paper/1907.05854/) (2019)
- [WeChat Neural Machine Translation Systems for WMT20](https://mlsanity.com/paper/2010.00247/) (2020)
- [Microsoft Research Asia's Systems for WMT19](https://mlsanity.com/paper/1911.06191/) (2019)
- [Online Learning for Effort Reduction in Interactive Neural Machine Translation](https://mlsanity.com/paper/1802.03594/) (2018)
- [A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation](https://mlsanity.com/paper/1805.01553/) (2018)
- [Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice](https://mlsanity.com/paper/1810.07778/) (2018)
- [The Volctrans Machine Translation System for WMT20](https://mlsanity.com/paper/2010.14806/) (2020)
- [Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort](https://mlsanity.com/paper/2105.13385/) (2021)
- [A Shared Task on Bandit Learning for Machine Translation](https://mlsanity.com/paper/1707.09050/) (2017)
- [Active2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation](https://mlsanity.com/paper/2103.06490/) (2021)
- [Can Active Learning Experience Be Transferred?](https://mlsanity.com/paper/1608.00667/) (2016)
- [A User-Study on Online Adaptation of Neural Machine Translation to Human Post-Edits](https://mlsanity.com/paper/1712.04853/) (2017)
- [Machine Translation System Selection from Bandit Feedback](https://mlsanity.com/paper/2002.09646/) (2020)

## Built on by (most cited first, 5 of 5)

- [A Survey of Active Learning for Natural Language Processing](https://mlsanity.com/paper/2210.10109/) (2022)
- [How to Select Datapoints for Efficient Human Evaluation of NLG Models?](https://mlsanity.com/paper/2501.18251/) (2025)
- [Quality and Quantity of Machine Translation References for Automatic Metrics](https://mlsanity.com/paper/2401.01283/) (2024)
- [EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only](https://mlsanity.com/paper/2306.11823/) (2023)
- [Reassessing Active Learning Adoption in Contemporary NLP: A Community Survey](https://mlsanity.com/paper/2503.09701/) (2025)

## Abstract (arXiv)

Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active learning approaches for Machine Translation assume the existence of a pool of sentences in a source language, and rely on human annotators to provide translations or post-edits, which can still be costly. In this article, we assume a real world human-in-the-loop scenario in which: (i) the source sentences may not be readily available, but instead arrive in a stream; (ii) the automatic translations receive feedback in the form of a rating, instead of a correct/edited translation, since the human-in-the-loop might be a user looking for a translation, but not be able to provide one. To tackle the challenge of deciding whether each incoming pair source-translations is worthy to query for human feedback, we resort to a number of stream-based active learning query strategies. Moreover, since we not know in advance which query strategy will be the most adequate for a certain language pair and set of Machine Translation models, we propose to dynamically combine multiple strategies using prediction with expert advice. Our experiments show that using active learning allows to converge to the best Machine Translation systems with fewer human interactions. Furthermore, combining multiple strategies using prediction with expert advice often outperforms several individual active learning strategies with even fewer interactions.