paper-with-me

Papers

Dynamic Memory Induction Networks for Few-Shot Text Classification

2020-05-12 · ACL 2020 6 · Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu

This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification. The model utilizes dynamic routing to provide more flexibility to memory-based few-shot learning in order to better adapt the support sets, which is a critical capacity of few-shot classification models. Based on that, we further develop induction models with query information, aiming to enhance the generalization ability of meta-learning. The proposed model achieves new state-of-the-art results on the miniRCV1 and ODIC dataset, improving the best performance (accuracy) by 2~4%. Detailed analysis is further performed to show the effectiveness of each component.

📄 PDF Abstract BibTeX arXiv:2005.05727

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationFew-Shot LearningFew-Shot Text ClassificationGeneral ClassificationMeta-Learningtext-classificationText Classification

Similar Papers 제목 키워드 기반

Induction Networks for Few-Shot Text Classification

2019-02-27 · IJCNLP 2019 11 · Ruiying Geng, Binhua Li, Yongbin Li, Xiaodan Zhu 외

Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new …

Few-Shot Text ClassificationGeneral Classificationintent-classificationIntent Classification+4

Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning

2024-07-09 · Joy Crosbie, Ekaterina Shutova

Large language models (LLMs) have shown a remarkable ability to learn and perform complex tasks through in-context learning (ICL). However, a comprehensive understanding of its internal mechanisms is still lacking. This …

In-Context Learning

Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks

2026-05-02 · Jie-Jing Shao, Haiyan Yin, Yueming Lyu, Xingrui Yu 외 arxiv

Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into…

Memory-Modular Classification: Learning to Generalize with Memory Replacement

2025-04-08 · Dahyun Kang, Ahmet Iscen, Eunchan Jo, Sua Choi 외

We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, …

Classificationimage-classificationImage ClassificationMemorization+1

GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer

2026-02-03 · Junmo Cho, Suhan Kim, Sangjune An, Minsu Kim 외 arxiv

Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based promp…

Few-Shot Text ClassificationQuestion Answering