paper-with-me

Papers

Addressing Exposure Bias With Document Minimum Risk Training: Cambridge at the WMT20 Biomedical Translation Task

2020-10-11 · WMT (EMNLP) 2020 11 · Danielle Saunders, Bill Byrne

The 2020 WMT Biomedical translation task evaluated Medline abstract translations. This is a small-domain translation task, meaning limited relevant training data with very distinct style and vocabulary. Models trained on such data are susceptible to exposure bias effects, particularly when training sentence pairs are imperfect translations of each other. This can result in poor behaviour during inference if the model learns to neglect the source sentence. The UNICAM entry addresses this problem during fine-tuning using a robust variant on Minimum Risk Training. We contrast this approach with data-filtering to remove `problem' training examples. Under MRT fine-tuning we obtain good results for both directions of English-German and English-Spanish biomedical translation. In particular we achieve the best English-to-Spanish translation result and second-best Spanish-to-English result, despite using only single models with no ensembling.

📄 PDF Abstract BibTeX arXiv:2010.05333

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceTranslation

Similar Papers 제목 키워드 기반

On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation

2020-05-07 · ACL 2020 6 · Chaojun Wang, Rico Sennrich

The standard training algorithm in neural machine translation (NMT) suffers from exposure bias, and alternative algorithms have been proposed to mitigate this. However, the practical impact of exposure bias is under deba…

HallucinationMachine TranslationNMTTranslation

COMO: Closed-Loop Optical Molecule Recognition with Minimum Risk Training

2026-04-26 · Zhuoqi Lyu, Qing Ke arxiv

Optical chemical structure recognition (OCSR) translates molecular images into machine-readable representations like SMILES strings or molecular graphs, but remains challenging in real-world documents due to inexhaustibl…

Choosing Online Experiment Designs under Interference in Ads, Recommendations, and Member-Experience Systems

2026-05-24 · Prashant Shekhar, Caroline Howard arxiv

Online experiments in ads, recommendation, and member-experience systems are often planned before the dominant interference mechanism is known. A treatment may propagate through budgets, inventory, producer exposure, gra…

Options on CPPI with guaranteed minimum equity exposure

2019-02-18

In the present paper we provide a two-step principal protection strategy obtained by combining a modification of the Constant Proportion Portfolio Insurance (CPPI) algorithm and a classical Option Based Portfolio Insuran…

Mitigating Exposure Bias in Risk-Aware Time Series Forecasting with Soft Tokens

2025-12-10 · Alireza Namazi, Amirreza Dolatpour Fathkouhi, Heman Shakeri arxiv

Autoregressive forecasting is central to predictive control in diabetes and hemodynamic management, where different operating zones carry different clinical risks. Standard models trained with teacher forcing suffer from…

Time Series ForecastingTrajectory Forecasting