paper-with-me

Papers

Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics

2022-03-29 · Findings (ACL) 2022 5 · Jiannan Xiang, Huayang Li, Yahui Liu, Lemao Liu, Guoping Huang, Defu Lian, Shuming Shi

Current practices in metric evaluation focus on one single dataset, e.g., Newstest dataset in each year's WMT Metrics Shared Task. However, in this paper, we qualitatively and quantitatively show that the performances of metrics are sensitive to data. The ranking of metrics varies when the evaluation is conducted on different datasets. Then this paper further investigates two potential hypotheses, i.e., insignificant data points and the deviation of Independent and Identically Distributed (i.i.d) assumption, which may take responsibility for the issue of data variance. In conclusion, our findings suggest that when evaluating automatic translation metrics, researchers should take data variance into account and be cautious to claim the result on a single dataset, because it may leads to inconsistent results with most of other datasets.

📄 PDF Abstract BibTeX arXiv:2203.15858

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits

2023-05-31 · Zhuokai Zhao, Takumi Matsuzawa, William Irvine, Michael Maire 외

Proper evaluations are crucial for better understanding, troubleshooting, interpreting model behaviors and further improving model performance. While using scalar-based error metrics provides a fast way to overview model…

3D Point Cloud Classificationobject-detectionObject DetectionPoint Cloud Classification

Revisiting Outer Optimization in Adversarial Training

2022-09-02 · Ali Dabouei, Fariborz Taherkhani, Sobhan Soleymani, Nasser M. Nasrabadi

Despite the fundamental distinction between adversarial and natural training (AT and NT), AT methods generally adopt momentum SGD (MSGD) for the outer optimization. This paper aims to analyze this choice by investigating…

Testing the Limits of Machine Translation from One Book

2025-08-08 · Jonathan Shaw, Dillon Mee, Timothy Khouw, Zackary Leech 외 arxiv

Current state-of-the-art models demonstrate capacity to leverage in-context learning to translate into previously unseen language contexts. Tanzer et al. [2024] utilize language materials (e.g. a grammar) to improve tran…

Machine Translation

Semantic features of object concepts generated with GPT-3

2022-02-08 · Hannes Hansen, Martin N. Hebart

Semantic features have been playing a central role in investigating the nature of our conceptual representations. Yet the enormous time and effort required to empirically sample and norm features from human raters has re…

Gradient Estimation with Discrete Stein Operators

2022-02-19 · Jiaxin Shi, Yuhao Zhou, Jessica Hwang, Michalis K. Titsias 외

Gradient estimation -- approximating the gradient of an expectation with respect to the parameters of a distribution -- is central to the solution of many machine learning problems. However, when the distribution is disc…