GlassyWing / transformer-word-segmenter
Sequence labeling base on universal transformer (Transformer encoder) and CRF; 基于Universal Transformer + CRF 的中文分词和词性标注
☆154Updated 5 years ago
Related projects: ⓘ
- 中文预训练XLNet模型: Pre-Trained Chinese XLNet_Large☆228Updated 5 years ago
- 利用预训练的中文模型实现基于bert的语义匹配模型 数据集为LCQMC官方数据☆194Updated 4 years ago
- 将百度ernie的paddlepaddle模型转成tensorflow模型☆177Updated 4 years ago
- DistilBERT for Chinese 海量中文预训练蒸馏bert模型☆89Updated 4 years ago
- bert chinese similarity☆139Updated 4 years ago
- TensorFlow code and pre-trained models for BERT and ERNIE☆143Updated 5 years ago
- Keras solution of Chinese NER task using BiLSTM-CRF/BiGRU-CRF/IDCNN-CRF model with Pretrained Language Model: supporting BERT/RoBERTa/ALB…☆12Updated last year
- transform multi-label classification as sentence pair task, with more training data and information☆179Updated 4 years ago
- 基于BERT的中文序列标注☆142Updated 5 years ago
- ☆125Updated this week
- transformer crf 命名实体识别☆104Updated 5 years ago
- use ELMo in chinese environment☆104Updated 5 years ago
- using bilstm-crf,bert and other methods to do sequence tagging task☆414Updated last year
- Deep contextualized word representations for Chinese☆152Updated 4 years ago
- 搜集、整理、发布 预训练 中文 词向量/字向量，与 有志之士 共同 促进 中文 自然语言处理 的 发展。☆145Updated 6 years ago
- 基于轻量级的albert实现albert+BiLstm+CRF☆87Updated last year
- Bert finetune for CMRC2018, CJRC, DRCD, CHID, C3☆182Updated 4 years ago
- 个人基于谷歌开源的BERT编写的文本分类器（基于微调方式），可自由加载NLP领域知名的预训练语言模型BERT、Bert-wwm、Roberta、ALBert以及ERNIE1.0☆160Updated 4 years ago
- ☆278Updated 3 years ago
- 中文语料 Bert finetune（Fine-tune Chinese for BERT）☆80Updated 5 years ago
- Neural word segmentation with rich pretraining, code for ACL 2017 paper☆167Updated 5 years ago
- 文本匹配的相关模型DSSM,ESIM,ABCNN,BIMPM等，数据集为LCQMC官方数据☆466Updated 2 years ago
- Python toolkit for Chinese Language Understanding(CLUE) Evaluation benchmark☆127Updated last year
- 序列化标注工具，基于PyTorch实现BLSTM-CNN-CRF模型，CoNLL 2003 English NER测试集F1值为91.10%（word and char feature）。☆362Updated 6 years ago
- datagrand 2019 information extraction competition rank9☆130Updated 4 years ago
- 2019年百度的实体链指比赛（ccks2019），一个baseline☆114Updated 5 years ago
- 中文自然语言的实体抽取和意图识别（Natural Language Understanding），可选Bi-LSTM + CRF 或者 IDCNN + CRF☆179Updated 5 years ago
- 基于Bi-GRU + CRF 的中文机构名、人名识别, 支持google bert模型☆164Updated 5 years ago
- Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"☆136Updated 3 years ago
- 整理一下在keras中使用T5模型的要点☆171Updated 2 years ago