mlsanityData to 7 Oct 2026

Fixing exposure bias with imitation learning needs powerful oracles

arXiv 2109.04114 ↗First posted 9 Sep 2021cs.CL cs.LGcited by 3

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

We apply imitation learning (IL) to tackle the NMT exposure bias problem with error-correcting oracles, and evaluate an SMT lattice-based oracle which, despite its excellent performance in an unconstrained oracle translation task, turned out to be too pruned and idiosyncratic to serve as the oracle for IL.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 6 of its 15 references that are in the map. First posted on arXiv 9 Sep 2021.

Builds on

6 of 15 references.

References · 6

  1. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  2. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  3. 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
  4. 2014Reinforcement and Imitation Learning via Interactive No-Regret Learningcited by 116
  5. 2015Minimum Risk Training for Neural Machine Translationcited by 114
  6. 2017Bandit Structured Prediction for Neural Sequence-to-Sequence Learningcited by 31

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2024Imitating Language via Scalable Inverse Reinforcement Learningcited by 21
  2. 2023A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Trainingcited by 16
  3. 2023Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcriptscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2020Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning
  2. 2020Policy Improvement via Imitation of Multiple Oracles ↗
  3. 2020The MAGICAL Benchmark for Robust Imitation
  4. 2023Selective Sampling and Imitation Learning via Online Regression
  5. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  6. 2024Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning
  7. 2021MobILE: Model-Based Imitation Learning From Observation Alone
  8. 2025Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement