Machine learningDeep learning / NLP / CV
[需翻译标题：BERT-based Classification...]
BERT-based Classification 通过在标注文本数据集上对谷歌的 Bidirectional Encoder Representations from Transformers 模型进行微调，用特定任务的分类层替换通用的预训练头部。它利用了数亿预训练参数的深度双向上下文，在具有相对适量标注数据的短文本和中等长度文本分类任务上实现了最先进的准确率。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
+60 more
来源
- Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics. DOI: 10.18653/v1/N19-1423 ↗
- Sun, C., Qiu, X., Xu, Y., & Huang, X. (2019). How to Fine-Tune BERT for Text Classification? In China National Conference on Chinese Computational Linguistics (CCL 2019), Lecture Notes in Computer Science, vol 11856, pp. 194–206. Springer. DOI: 10.1007/978-3-030-32381-3_16 ↗
如何引用本页
ScholarGate. (2026, June 3). Bidirectional Encoder Representations from Transformers for Text Classification. ScholarGate. https://scholargate.app/zh/deep-learning/bert-based-classification
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →被引用于
基于领域自适应BERT的分类领域自适应命名实体识别领域自适应问答基于域自适应的 RoBERTa 分类领域自适应句子嵌入 (Domain-Adaptive Sentence Embeddings)领域自适应情感分析领域自适应文本摘要可解释的BERT分类可解释命名实体识别可解释问答可解释的 RoBERTa 分类可解释句子嵌入可解释情感分析可解释主题建模可解释 Transformer微调 BERT 分类微调Doc2Vec微调长短期记忆网络 (Fine-Tuned LSTM)微调命名实体识别微调问答RoBERTa-based 分类微调微调句嵌入微调文本摘要微调主题建模微调Transformer微调视觉Transformer微调 Word2Vec (Fine-Tuned Word2Vec)门控循环单元 (GRU)LDA主题模型长短期记忆网络（LSTM）多语言问答基于多语言 RoBERTa 的分类多语言句子嵌入多语言情感分析多语言 Transformer多模态命名实体识别多模态问题解答多模态 RoBERTa 分类多模态文本摘要多模态Transformer多模态视觉变换器NMF 主题模型循环神经网络基于RoBERTa的分类自监督LDA主题模型自监督句子嵌入自监督主题建模自监督Transformer半监督式BERT分类半监督LDA主题模型半监督问答基于RoBERTa的半监督分类半监督句子嵌入半监督情感分析半监督式 Transformer句子嵌入主题建模BERT 기반 전이 학습LSTM 迁移学习命名实体识别的迁移学习基于句子嵌入的迁移学习迁移学习与文本摘要主题建模迁移学习弱监督BERT分类弱监督问答弱监督 RoBERTa 分类弱监督句子嵌入弱监督主题建模弱监督 Transformer弱监督词向量 (Weakly Supervised Word2Vec)