paper-with-me

Papers

Sample Efficient Model Evaluation

2021-09-24 · Emine Yilmaz, Peter Hayes, Raza Habib, Jordan Burgess, David Barber

Labelling data is a major practical bottleneck in training and testing classifiers. Given a collection of unlabelled data points, we address how to select which subset to label to best estimate test metrics such as accuracy, $F_1$ score or micro/macro $F_1$. We consider two sampling based approaches, namely the well-known Importance Sampling and we introduce a novel application of Poisson Sampling. For both approaches we derive the minimal error sampling distributions and how to approximate and use them to form estimators and confidence intervals. We show that Poisson Sampling outperforms Importance Sampling both theoretically and experimentally.

📄 PDF Abstract BibTeX arXiv:2109.12043

Code (0)

등록된 구현이 없습니다.

Tasks

model

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

A Human-machine Collaborative Framework for Evaluating Malevolence in Dialogues

2021-08-01 · ACL 2021 5 · Yangjun Zhang, Pengjie Ren, Maarten de Rijke

Conversational dialogue systems (CDSs) are hard to evaluate due to the complexity of natural language. Automatic evaluation of dialogues often shows insufficient correlation with human judgements. Human evaluation is rel…

Dialogue Evaluation

Improving the evaluation of samplers on multi-modal targets

2025-04-11 · Louis Grenioux, Maxence Noble, Marylou Gabrié

Addressing multi-modality constitutes one of the major challenges of sampling. In this reflection paper, we advocate for a more systematic evaluation of samplers towards two sources of difficulty that are mode separation…

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework

2023-05-29 · Yangyi Chen, Hongcheng Gao, Ganqu Cui, Lifan Yuan 외

Textual adversarial attacks can discover models' weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The long-lasting adversarial attack-and-defense arms race in Natural Language Processin…

Adversarial Attack

Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment

2020-11-26 · Jeonghoon Park, Kyungmin Jo, Daehoon Gwak, Jimin Hong 외

We evaluate the out-of-distribution (OOD) detection performance of self-supervised learning (SSL) techniques with a new evaluation framework. Unlike the previous evaluation methods, the proposed framework adjusts the dis…

Out-of-Distribution DetectionOut of Distribution (OOD) DetectionSelf-Supervised Learning

Depth $F_1$: Improving Evaluation of Cross-Domain Text Classification by Measuring Semantic Generalizability

2024-06-20 · Parker Seegmiller, Joseph Gatto, Sarah Masud Preum

Recent evaluations of cross-domain text classification models aim to measure the ability of a model to obtain domain-invariant performance in a target domain given labeled samples in a source domain. The primary strategy…

ClassificationCross-Domain Text Classificationtext-classificationText Classification+1