logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Best-Fit Document: Enhancing Compositional Generalization in Multi-label Text Classification

delete2026-01-01
delete0
PRE
AI
郭
郭恒亮 (Hengliang Guo)
S
Shengguang Zhu
H
Haitao Wang
J
Junjie Chen
J
Jiaru Li
R
Ruikai Ma
G
Gang Wu *
DOI：10.1007/978-981-95-3349-7_25delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
多标签文本分类（MLTC）提出了一个复杂挑战，要求分类器为每个文档分配多个标签，导致大规模语料库中出现多样的标签组合。尽管传统MLTC任务取得了显著进展，但现有研究常忽视组合泛化（CG）挑战对模型性能的影响。当前模型难以泛化到新颖且复杂的标签组合，这些组合通常由基础标签构成。本研究通过提出一种简单且可扩展的数据分组方法，即最佳匹配文档（BFD），该方法基于文档长度优化大规模训练数据，以增强分类器对新颖标签组合的建模能力。在四个具有专业数据划分的数据集上对BFD进行了全面评估。实验结果表明，该方法显著提升了分类模型在评估基准上的CG能力。
Keyword:
Multi-label Text Classification
Compositional Generalization

期刊

N
NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING, NLPCC 2025, PT III
IF:
0
论文数:
32
被引数:
0

机构

Z
zhengzhou university
学者数:
1.3W
论文数: 3.5K
被引数: 2
引用论文

引用论文

Training Language Models with Memory Augmentation
errProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
IF0
err2022-01-01
err0
errOAAI
errZexuan Zhong; Tao Lei; Danqi Chen
err分享
err收藏
Prompt-Based Generative Multi-label Emotion Prediction with Label Contrastive Learning
errLecture Notes in Computer Science
IF0
err2022-01-01
err0
PREAI
errChai,Yuyang; Teng,Chong; Fei,Hao; Wu,Shengqiong; Li,Jingye; Cheng,Ming; Ji,Donghong; Li,Fei
err分享
err收藏
Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach
errProceedings of the AAAI Conference on Artificial Intelligence
IF0
err2024-03-24
err0
errOAAI
errYuyang Chai; Zhuang Li; Jiahui Liu; Lei Chen; Fei Li; Donghong Ji; Chong Teng
err分享
err收藏
MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network
errProceedings of the 12th International Conference on Agents and Artificial Intelligence
IF0
err2020-01-01
err0
errOAAI
errAnkit Pal; Muru Selvakumar; Malaikannan Sankarasubbu
err分享
err收藏
Exploring Contrastive Learning for Long-Tailed Multi-label Text Classification
errLecture Notes in Computer Science
IF0
err2024-01-01
err0
PREAI
errAudibert,Alexandre; Gauffre,Aurélien; Amini,Massih-Reza
err分享
err收藏
Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing
errProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
IF0
err2022-01-01
err0
errOAAI
errLinlu Qiu; Peter Shaw; Panupong Pasupat; Tianze Shi; Jonathan Herzig; Emily Pitler; Fei Sha; Kristina Toutanova
err分享
err收藏
Label-Specific Document Representation for Multi-Label Text Classification
errProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
IF0
err2019-01-01
err0
errOAAI
errLin Xiao; Xin Huang; Boli Chen; Liping Jing
err分享
err收藏
Disentangled Sequence to Sequence Learning for Compositional Generalization
errProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
IF0
err2022-01-01
err0
errOAAI
errHao Zheng; Mirella Lapata
err分享
err收藏
Emotion Classification by Jointly Learning to Lexiconize and Classify
errProceedings of the 28th International Conference on Computational Linguistics
IF0
err2020-01-01
err0
errOAAI
errDeyu Zhou; Shuangzhi Wu; Qing Wang; Jun Xie; Zhaopeng Tu; Mu Li
err分享
err收藏
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation
errProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
IF0
err2022-01-01
err0
PREAI
errLi,Zhuang; Qu,Lizhen; Xu,Qiongkai; Wu,Tongtong; Zhan,Tianyang; Haffari,Gholamreza
err分享
err收藏
学者 查看更多内容