paper-with-me

Papers

$\textit{GeoHard}$: Towards Measuring Class-wise Hardness through Modelling Class Semantics

2024-07-17 · Fengyu Cai, Xinran Zhao, Hongming Zhang, Iryna Gurevych, Heinz Koeppl

Recent advances in measuring hardness-wise properties of data guide language models in sample selection within low-resource scenarios. However, class-specific properties are overlooked for task setup and learning. How will these properties influence model learning and is it generalizable across datasets? To answer this question, this work formally initiates the concept of $\textit{class-wise hardness}$. Experiments across eight natural language understanding (NLU) datasets demonstrate a consistent hardness distribution across learning paradigms, models, and human judgment. Subsequent experiments unveil a notable challenge in measuring such class-wise hardness with instance-level metrics in previous works. To address this, we propose $\textit{GeoHard}$ for class-wise hardness measurement by modeling class geometry in the semantic embedding space. $\textit{GeoHard}$ surpasses instance-level metrics by over 59 percent on $\textit{Pearson}$'s correlation on measuring class-wise hardness. Our analysis theoretically and empirically underscores the generality of $\textit{GeoHard}$ as a fresh perspective on data diagnosis. Additionally, we showcase how understanding class-wise hardness can practically aid in improving task learning.

📄 PDF Abstract BibTeX arXiv:2407.12512

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

On the Robustness of Question Rewriting Systems to Questions of Varying Hardness

2023-11-12 · ACL 2022 5 · Hai Ye, Hwee Tou Ng, Wenjuan Han

In conversational question answering (CQA), the task of question rewriting~(QR) in context aims to rewrite a context-dependent question into an equivalent self-contained question that gives the same answer. In this paper…

Conversational Question AnsweringQuestion AnsweringQuestion Rewriting

The Complexity of Finding Local Optima in Contrastive Learning

2025-09-21 · Jingming Yan, Yiyuan Luo, Vaggos Chatziafratis, Ioannis Panageas 외 arxiv

Contrastive learning is a powerful technique for discovering meaningful data representations by optimizing objectives based on $\textit{contrastive information}$, often given as a set of weighted triplets $\{(x_i, y_i^+,…

Contrastive Learning

Estimating the hardness of SAT encodings for Logical Equivalence Checking of Boolean circuits

2022-10-04 · Alexander Semenov, Konstantin Chukharev, Egor Tarasov, Daniil Chivilikhin 외

In this paper we investigate how to estimate the hardness of Boolean satisfiability (SAT) encodings for the Logical Equivalence Checking problem (LEC). Meaningful estimates of hardness are important in cases when a conve…

On Measuring the Intrinsic Few-Shot Hardness of Datasets

2022-11-16 · Xinran Zhao, Shikhar Murty, Christopher D. Manning

While advances in pre-training have led to dramatic improvements in few-shot learning of NLP tasks, there is limited understanding of what drives successful few-shot adaptation in datasets. In particular, given a new dat…

Few-Shot Learning

Rademacher Observations, Private Data, and Boosting

2015-02-09 · Richard Nock, Giorgio Patrini, Arik Friedman

The minimization of the logistic loss is a popular approach to batch supervised learning. Our paper starts from the surprising observation that, when fitting linear (or kernelized) classifiers, the minimization of the lo…