面向小样本的文本分类方法研究与实现任务书
2020-02-18 17:31:36
1. 毕业设计(论文)主要内容:
1.前期知识储备:
通过阅读相关文献,了解小样本#65380;迁移学习#65380;文本分类#65380;主动学习等相关知识。
2.设计功能:
本设计的任务包括:
1)针对小样本训练数据容易产生过拟合问题,研究基于迁移学习的小样本文本分类方法;
2)收集民航员工各种社交媒体的文本信息,以分析民航员工不安全行为倾向为目标,寻找易于迁移学习的源域数据,并分析源域与目标域数据的特征与关联关系,从而构建面向民航员工不安全行为倾向分析的文本分类迁移学习模型并验证其有效性。
2. 毕业设计(论文)主要任务及要求
1.查阅15篇相关文献(不少于3篇外文文献),并每篇书写200—300字文献摘要(装订成册,带封面);
2.认真填写周记,完成至少1500字开题报告(“设计的目的及意义”至少800汉字;“基本内容和技术方案”至少400汉字;进度安排应尽可能详细;);
3.完成5000中文字以上的相关英文专业文献翻译,并装订成册(中英文一起,带封面);
4.完成方法研究、算法设计与实现;
5.按武汉理工大学理工类本科生毕业论文撰写规范撰写毕业论文,完成10000字以上的毕业论文;
6.进行论文答辩。
3. 毕业设计(论文)完成任务的计划与安排
1.2019/1/19—2019/2/28:确定选题,查阅文献,外文翻译和撰写开题报告;
2.2019/3/1—2019/4/30:系统架构、程序设计与开发、系统测试与完善;
3.2019/5/1—2019/5/25:撰写及修改毕业论文;
4.2019/5/26—2019/6/5:准备答辩。
4. 主要参考文献
[1] Howard J, Ruder S. Universal language model fine-tuning for text classification[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018, 1: 328-339.
[2] Wang Z, Qu Y, Chen L, et al. Label-aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition[C] //Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2018: 1-15.
[3] Rei M, S#248;gaard A. Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens[C] //Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2018: 293-302.
[4] Chung Y A, Lee H Y, Glass J. Supervised and Unsupervised Transfer Learning for Question Answering [C] //Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2018: 1585-1594.
[5] Huang L, Ji H, Cho K, et al. Zero-Shot Transfer Learning for Event Extraction [C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018, 1: 2160-2170.
[6] Dong X, de Melo G. A Helping Hand: Transfer Learning for Deep Sentiment Analysis[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018, 1: 2524-2534.
[7] Cao P, Chen Y, Liu K, et al. Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018: 182-192.
[8] Liu T, Zhang X, Zhou W, et al. Neural relation extraction via inner-sentence noise reduction and transfer learning [C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018: 2195-2205.
[9] Rios A, Kavuluru R. Few-Shot and Zero-Shot Multi-Label Learning for Structured Label Spaces[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018: 3132-3142.
[10] 任俊,胡晓峰,李宁.基于SDA与SVR混合模型的迁移学习预测算法.计算机科学,45(1):280-284 312.
[11] 张军.基于主动学习和迁移学习的文本情感预测研究[D].山西大学.2016.
[12] 刘川.面向小样本的文本分类模型及算法研究[D].电子科技大学.2017.