paper-with-me

홈 › Papers

Fixing exposure bias with imitation learning needs powerful oracles

2021-09-09 · Luca Hormann, Artem Sokolov

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.

📄 PDF Abstract BibTeX arXiv:2109.04114

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningNMTTranslation

Similar Papers 제목 키워드 기반

Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation

2022-04-03 · Findings (ACL) 2022 5 · Kushal Arora, Layla El Asri, Hareesh Bahuleyan, Jackie Chi Kit Cheung

Current language generation models suffer from issues such as repetition, incoherence, and hallucinations. An often-repeated hypothesis is that this brittleness of generation models is caused by the training and the gene…

Imitation LearningText Generation

Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training

2026-04-09 · Constantin Le Cleï, Nils Thuerey, Xiaoxiang Zhu arxiv

Conditional Diffusion Models are powerful surrogates for emulating complex spatiotemporal dynamics, yet they often fail to match the accuracy of deterministic neural emulators for high-precision tasks. In this work, we a…

Analyzing 'Near Me' Services: Potential for Exposure Bias in Location-based Retrieval

2020-11-14 · Ashmi Banerjee, Gourab K Patro, Linus W. Dietz, Abhijnan Chakraborty

The proliferation of smartphones has led to the increased popularity of location-based search and recommendation systems. Online platforms like Google and Yelp allow location-based search in the form of nearby feature to…

AttributeRecommendation SystemsRetrieval

Fairness of Exposure in Dynamic Recommendation

2023-09-05 · Masoud Mansoury, Bamshad Mobasher

Exposure bias is a well-known issue in recommender systems where the exposure is not fairly distributed among items in the recommendation results. This is especially problematic when bias is amplified over time as a few …

Exposure FairnessFairnessRecommendation Systems

Dynamic Scheduled Sampling with Imitation Loss for Neural Text Generation

2023-01-31 · Xiang Lin, Prathyusha Jwalapuram, Shafiq Joty

State-of-the-art neural text generation models are typically trained to maximize the likelihood of each token in the ground-truth sequence conditioned on the previous target tokens. However, during inference, the model n…

DecoderMachine TranslationText Generation