Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features

2024-09-06 · Miao Fan, Yeqi Bai, Mingming Sun, Ping Li

Relation classification (RC) plays a pivotal role in both natural language understanding and knowledge graph completion. It is generally formulated as a task to recognize the relationship between two entities of interest appearing in a free-text sentence. Conventional approaches on RC, regardless of feature engineering or deep learning based, can obtain promising performance on categorizing common types of relation leaving a large proportion of unrecognizable long-tail relations due to insufficient labeled instances for training. In this paper, we consider few-shot learning is of great practical significance to RC and thus improve a modern framework of metric learning for few-shot RC. Specifically, we adopt the large-margin ProtoNet with fine-grained features, expecting they can generalize well on long-tail relations. Extensive experiments were conducted by FewRel, a large-scale supervised few-shot RC dataset, to evaluate our framework: LM-ProtoNet (FGF). The results demonstrate that it can achieve substantial improvements over many baseline approaches.

📄 PDF Abstract BibTeX arXiv:2409.04009

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Engineering Few-Shot Learning Few-Shot Relation Classification Knowledge Graph Completion Metric Learning Natural Language UnderstandingRelationRelation ClassificationSentence

Large Margin Few-Shot Learning

2018-07-08 · Yong Wang, Xiao-Ming Wu, Qimai Li, Jiatao Gu 외

The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a…

Few-Shot Learning General Classification

SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition

2022-10-17 · Jianing Wang, Chengcheng Han, Chengyu Wang, Chuanqi Tan 외

Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, which ignores the information of entity bou…

Few-shot NER Named Entity Recognition Named Entity Recognition (NER)

A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification

2020-12-01 · COLING 2020 8 · Haopeng Ren, Yi Cai, Xiaofeng Chen, Guohua Wang 외

Relation Classification (RC) plays an important role in natural language processing (NLP). Current conventional supervised and distantly supervised RC models always make a closed-world assumption which ignores the emerge…

Few-Shot Learning Few-Shot Relation Classification Lifelong learning Relation+2

Few-shot Text Classification with Distributional Signatures

2019-08-16 · ICLR 2020 1 · Yujia Bao, Menghua Wu, Shiyu Chang, Regina Barzilay

In this paper, we explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly …

Classification Few-Shot Text Classification General Classification Meta-Learning+3

Strategies to Improve Few-shot Learning for Intent Classification and Slot-Filling

2022-07-01 · NAACL (SUKI) 2022 7 · Samyadeep Basu, Amr Sharaf, Karine Ip Kiun Chong, Alex Fischer 외

Intent classification (IC) and slot filling (SF) are two fundamental tasks in modern Natural Language Understanding (NLU) systems. Collecting and annotating large amounts of data to train deep learning models for such sy…

Contrastive Learning Data Augmentation Few-Shot Learning intent-classification+6