paper-with-me

홈 › Papers

Boosting Few-Shot Text Classification via Distribution Estimation

2023-03-26 · Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Fenglong Ma, Xiao-Ming Wu, Hongyang Chen, Hong Yu, Xianchao Zhang

Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain. However, directly applying this approach to few-shot text classification is challenging, since leveraging the statistics of known classes with sufficient samples to calibrate the distributions of novel classes may cause negative effects due to serious category difference in text domain. To alleviate this issue, we propose two simple yet effective strategies to estimate the distributions of the novel classes by utilizing unlabeled query samples, thus avoiding the potential negative transfer issue. Specifically, we first assume a class or sample follows the Gaussian distribution, and use the original support set and the nearest few query samples to estimate the corresponding mean and covariance. Then, we augment the labeled samples by sampling from the estimated distribution, which can provide sufficient supervision for training the classification model. Extensive experiments on eight few-shot text classification datasets show that the proposed method outperforms state-of-the-art baselines significantly.

📄 PDF Abstract BibTeX arXiv:2303.16764

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationFew-Shot Image ClassificationFew-Shot Text Classificationimage-classificationImage Classificationtext-classificationText Classification

Similar Papers 제목 키워드 기반

PromptBoosting: Black-Box Text Classification with Ten Forward Passes

2022-12-19 · Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang 외

We describe PromptBoosting, a query-efficient procedure for building a text classifier from a neural language model (LM) without access to the LM's parameters, gradients, or hidden representations. This form of "black-bo…

ClassificationLanguage Modellingtext-classificationText Classification

Language models are weak learners

2023-06-25 · NeurIPS 2023 11

A central notion in practical and theoretical machine learning is that of a $\textit{weak learner}$, classifiers that achieve better-than-random performance (on any given distribution over data), even by a small margin. …

Few-Shot LearningLanguage ModellingLarge Language Model

Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing

2024-05-06 · Han Liu, Siyang Zhao, Xiaotong Zhang, Feng Zhang 외

Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring…

Binary ClassificationClassificationLanguage ModellingMulti-class Classification+3

Boosting coherence of language models

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Naturality of long-term information structure -- coherence -- remains a challenge in language generation. Large language models have insufficiently learned such structure, as their long-form generations differ from natur…

Text Generation

Description Boosting for Zero-Shot Entity and Relation Classification

2024-06-04 · Gabriele Picco, Leopold Fuchs, Marcos Martínez Galindo, Alberto Purpura 외

Zero-shot entity and relation classification models leverage available external information of unseen classes -- e.g., textual descriptions -- to annotate input text data. Thanks to the minimum data requirement, Zero-Sho…

RelationRelation ClassificationZero-Shot Learning