中文
相关论文

相关论文: Debiasing Made State-of-the-art: Revisiting the Si…

200 篇论文

Weakly-supervised text classification aims to induce text classifiers from only a few user-provided seed words. The vast majority of previous work assumes high-quality seed words are given. However, the expert-annotated seed words are…

计算与语言 · 计算机科学 2021-04-21 Yiping Jin , Akshay Bhatia , Dittaya Wanvarie

In weakly-supervised text classification, only label names act as sources of supervision. Predominant approaches to weakly-supervised text classification utilize a two-phase framework, where test samples are first assigned pseudo-labels and…

计算与语言 · 计算机科学 2022-10-14 Seongmin Park , Jihwa Lee

Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification…

信息检索 · 计算机科学 2018-09-13 Yu Meng , Jiaming Shen , Chao Zhang , Jiawei Han

Dataless text classification, i.e., a new paradigm of weakly supervised learning, refers to the task of learning with unlabeled documents and a few predefined representative words of categories, known as seed words. The recent generative…

计算与语言 · 计算机科学 2021-12-07 Bing Wang , Yue Wang , Ximing Li , Jihong Ouyang

Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…

计算机视觉与模式识别 · 计算机科学 2020-06-30 Eric Arazo , Diego Ortego , Paul Albert , Noel E. O'Connor , Kevin McGuinness

Etremely Weakly Supervised Text Classification (XWS-TC) refers to text classification based on minimal high-level human guidance, such as a few label-indicative seed words or classification instructions. There are two mainstream approaches…

计算与语言 · 计算机科学 2023-05-23 Zihan Wang , Tianle Wang , Dheeraj Mekala , Jingbo Shang

In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some…

机器学习 · 统计学 2011-08-25 Christopher M. White , Sanjeev P. Khudanpur , Patrick J. Wolfe

Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static…

计算与语言 · 计算机科学 2023-10-23 Yunyi Zhang , Minhao Jiang , Yu Meng , Yu Zhang , Jiawei Han

Weeds present a significant challenge in agriculture, causing yield loss and requiring expensive control measures. Automatic weed detection using computer vision and deep learning offers a promising solution. However, conventional deep…

计算机视觉与模式识别 · 计算机科学 2024-05-14 Alzayat Saleh , Alex Olsen , Jake Wood , Bronson Philippa , Mostafa Rahimi Azghadi

Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionally, a supervised learning was used for training the models,…

计算机视觉与模式识别 · 计算机科学 2022-04-06 Jiwon Kim , Kwangrok Ryoo , Junyoung Seo , Gyuseong Lee , Daehwan Kim , Hansang Cho , Seungryong Kim

In this paper, we explore text classification with extremely weak supervision, i.e., only relying on the surface text of class names. This is a more challenging setting than the seed-driven weak supervision, which allows a few seed words…

计算与语言 · 计算机科学 2022-02-09 Zihan Wang , Dheeraj Mekala , Jingbo Shang

We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…

计算与语言 · 计算机科学 2024-01-02 Payam Karisani

This paper tackles the problem of semi-supervised learning when the set of labeled samples is limited to a small number of images per class, typically less than 10, problem that we refer to as barely-supervised learning. We analyze in depth…

计算机视觉与模式识别 · 计算机科学 2021-12-23 Thomas Lucas , Philippe Weinzaepfel , Gregory Rogez

Unsupervised image captioning is a challenging task that aims at generating captions without the supervision of image-sentence pairs, but only with images and sentences drawn from different sources and object labels detected from the…

计算与语言 · 计算机科学 2021-06-02 Ukyo Honda , Yoshitaka Ushiku , Atsushi Hashimoto , Taro Watanabe , Yuji Matsumoto

Our work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words. Recent works have focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and…

计算与语言 · 计算机科学 2023-11-17 Thi-Nhung Nguyen , Hoang Ngo , Kiem-Hieu Nguyen , Tuan-Dung Cao

User-generated reviews can be decomposed into fine-grained segments (e.g., sentences, clauses), each evaluating a different aspect of the principal entity (e.g., price, quality, appearance). Automatically detecting these aspects can be…

机器学习 · 计算机科学 2019-09-04 Giannis Karamanolakis , Daniel Hsu , Luis Gravano

Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models are gaining increasing popularity for text classification due…

计算与语言 · 计算机科学 2019-01-01 Yu Meng , Jiaming Shen , Chao Zhang , Jiawei Han

Existing backdoor defense methods are only effective for limited trigger types. To defend different trigger types at once, we start from the class-irrelevant nature of the poisoning process and propose a novel weakly supervised backdoor…

计算与语言 · 计算机科学 2022-11-01 Lesheng Jin , Zihan Wang , Jingbo Shang

Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting…

计算与语言 · 计算机科学 2021-02-24 Xinyang Zhang , Chenwei Zhang , Luna Xin Dong , Jingbo Shang , Jiawei Han

Fine tuning self supervised pretrained models using pseudo labels can effectively improve speech recognition performance. But, low quality pseudo labels can misguide decision boundaries and degrade performance. We propose a simple yet…

声音 · 计算机科学 2022-11-01 Zezhong Jin , Dading Zhong , Xiao Song , Zhaoyi Liu , Naipeng Ye , Qingcheng Zeng
‹ 上一页 1 2 3 10 下一页 ›