paper-with-me

Papers

SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification

2023-01-26 · Pranjal Aggarwal, Ameet Deshpande, Karthik Narasimhan

Extreme classification (XC) involves predicting over large numbers of classes (thousands to millions), with real-world applications like news article classification and e-commerce product tagging. The zero-shot version of this task requires generalization to novel classes without additional supervision. In this paper, we develop SemSup-XC, a model that achieves state-of-the-art zero-shot and few-shot performance on three XC datasets derived from legal, e-commerce, and Wikipedia data. To develop SemSup-XC, we use automatically collected semantic class descriptions to represent classes and facilitate generalization through a novel hybrid matching module that matches input instances to class descriptions using a combination of semantic and lexical similarity. Trained with contrastive learning, SemSup-XC significantly outperforms baselines and establishes state-of-the-art performance on all three datasets considered, gaining up to 12 precision points on zero-shot and more than 10 precision points on one-shot tests, with similar gains for recall@10. Our ablation studies highlight the relative importance of our hybrid matching module and automatically collected class descriptions.

📄 PDF Abstract BibTeX arXiv:2301.11309

Code (1)

princeton-nlp/semsup-xc 공식 구현 pytorch

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization

2022-02-26 · Austin W. Hanjie, Ameet Deshpande, Karthik Narasimhan

Zero-shot learning is the problem of predicting instances over classes not seen during training. One approach to zero-shot learning is providing auxiliary class information to the model. Prior work along this vein have l…

Semantic SimilaritySemantic Textual SimilarityWord EmbeddingsZero-shot Generalization+1

Extreme Zero-Shot Learning for Extreme Text Classification

2021-12-16 · NAACL 2022 7 · Yuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu 외

The eXtreme Multi-label text Classification (XMC) problem concerns finding most relevant labels for an input text instance from a large label set. However, the XMC setup faces two challenges: (1) it is not generalizable …

ClassificationMulti Label Text ClassificationMulti-Label Text Classificationtext-classification+2

Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?

2024-12-11 · Zihao Li, Lecheng Zheng, Bowen Jin, Dongqi Fu 외

While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipel…

Prompt Learningzero-shot-classificationZero-Shot Learning

Extreme Zero-Shot Learning for Extreme Text Classification

2022-01-16 · ACL ARR January 2022 1 · Anonymous

The eXtreme Multi-label text Classification (XMC) problem concerns finding most relevant labels for an input text instance from a large label set. However, the XMC setup faces two challenges: (1) it is not generalizable …

ClassificationMulti Label Text ClassificationMulti-Label Text Classificationtext-classification+2

All Labels Together: Low-shot Intent Detection with an Efficient Label Semantic Encoding Paradigm

2023-09-07 · Jiangshu Du, Congying Xia, Wenpeng Yin, TingTing Liang 외

In intent detection tasks, leveraging meaningful semantic information from intent labels can be particularly beneficial for few-shot scenarios. However, existing few-shot intent detection methods either ignore the intent…

AllDomain GeneralizationIntent Detection