Bo Han

Shared Tasks of the 2015 Workshop on Noisy User-generated Text: Twitter Lexical Normalization and Named Entity Recognition

2015 · The Association for Computational Linguistics

This paper presents the results of the two shared tasks associated with W-NUT 2015: (1) a text normalization task with 10 participants; and (2) a named entity tagging task with 8 participants. We outline the …

Masking: A New Perspective of Noisy Supervision

2018 · arXiv (Cornell University)

It is important to learn various types of classifiers given training data with noisy labels. Noisy labels, in the most popular noise model hitherto, are corrupted from ground-truth labels by an unknown noise transition matrix. …

Provably Consistent Partial-Label Learning

2020 · Neural Information Processing Systems

Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels. Even though many practical PLL methods have been proposed in the last two decades, there …

Learning to Augment Distributions for Out-of-Distribution Detection

2023 · arXiv (Cornell University)

Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD detection. Advanced works, despite their promising progress, may still fail in the open …

BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning

2024 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to instance-dependent noises. In this …

Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning

2024 · arXiv (Cornell University)

Noisy correspondence that refers to mismatches in cross-modal data pairs, is prevalent on human-annotated or web-crawled datasets. Prior approaches to leverage such data mainly consider the application of uni-modal noisy label learning without amending the …

Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models

2024 · arXiv (Cornell University)

Physics problems constitute a significant aspect of reasoning, necessitating complicated reasoning ability and abundant physics knowledge. However, existing large language models (LLMs) frequently fail due to a lack of knowledge or incorrect knowledge application. To …