Saved in:
Bibliographic Details
Main Authors: Fan, Miao, Bai, Yeqi, Sun, Mingming, Li, Ping
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.04009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916384655540224
author Fan, Miao
Bai, Yeqi
Sun, Mingming
Li, Ping
author_facet Fan, Miao
Bai, Yeqi
Sun, Mingming
Li, Ping
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_04009
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features
Fan, Miao
Bai, Yeqi
Sun, Mingming
Li, Ping
Computation and Language
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.
title Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features
topic Computation and Language
url https://arxiv.org/abs/2409.04009