wangbq18's repositories
distillation_model_keras_bert
CNN、BiLSTM、Bert(3layers)对Bert(12layers)模型的蒸馏的keras实现
Doc2EDAG_tf
Doc2EDAG的tensorflow实现
BIO-R-BERT
R-BERT on DDI Bio dataset
-DGCNN
在苏剑林老师和闫广庆老师的代码上改了一下,可以在Jupyter上直接运行。
2020-KBQA
知识图谱问答系统
AdvAttack
基于Adversarial Attack的问题等价性判别比赛 第六开源
BDCI2019-SENTIMENT-CLASSIFICATION
CCF BDCI 2019 互联网新闻情感分析 复赛top1解决方案
Capsule-NLU
Joint Slot Filling and Intent Detection via Capsule Neural Networks (ACL'19) https://arxiv.org/abs/1812.09471
CCF-BDCI-ABSA
CCF BDCI 金融信息负面及主体判定第三名方案
CCF_BDCI_2019_datafountain350
CCF BDCI 2019 互联网新闻情感分析 复赛top8 代码
ccf_financial_negative
CCF BDCI 金融信息负面及主体判定 冠军代码
ccks2019-ckbqa-4th-codes
中文知识库问答代码,在CCKS2019 CKBQA评测获得67.6%的F值,第四名
CNSD
中文自然语言推理数据集(A large-scale Chinese Nature language inference and Semantic similarity calculation Dataset)
Correlation-between-requirements-and-achievements
CCF BDCI 2019 “技术需求”与“技术成果”项目之间关联度计算模型 复赛B榜top1解决方案
DeepCT
DeepCT uses BERT to generate novel, context-aware bag-of-words term weights for documents and queries.
DGCNN
Dilation Gate CNN For Machine Reading Comprehension
diac
Adversarial Attack for Question Equivalent Problem
fancy-nlp
NLP for human. A fast and esay-to-use natural language processing (NLP) toolkit, satisfying your imagination about NLP.
gender-unbiased_BERT-based_pronoun_resolution
Source code for the ACL workshop paper and Kaggle competition by Google AI team
roberta-wwm-base-distill
this is roberta wwm base distilled model which was distilled from roberta wwm base by roberta wwm large
sequence_tagging
using bilstm-crf,bert and other methods to do sequence tagging task
Transformer-based-pretrained-model-for-event-extraction
使用基于Transformer的预训练模型在ACE2005数据集上进行事件抽取任务
wsdm2020-solution
Solution of team funny in WSDM2020
zhihu-findexp
2019年知乎看山杯专家发现算法大赛第六名完整解决方案