TernenceWind / replaceSynbycilin
利用哈工大同义词林替换问答文本内的同义词进行语料扩充
☆36Updated 5 years ago
Alternatives and similar repositories for replaceSynbycilin:
Users that are interested in replaceSynbycilin are comparing it to the libraries listed below
- albert + lstm + crf实体识别,pytorch实现。识别的主要实体是人名、地名、机构名和时间。albert + lstm + crf (named entity recognition)☆136Updated 2 years ago
- 中国中文信息学会社会媒体处理专业委员会举办的2019届中文人机对话之自然语言理解竞赛☆74Updated 4 years ago
- NLP Predtrained Embeddings, Models and Datasets Collections(NLP_PEMDC). The collection will keep updating.☆64Updated 5 years ago
- 基于ltp的简单评论观点抽取模块☆116Updated 6 years ago
- TensorFlow code and pre-trained models for BERT☆58Updated 3 years ago
- WordMultiSenseDisambiguation, chinese multi-wordsense disambiguation based on online bake knowledge base and semantic embedding similarit…☆124Updated 6 years ago
- some baselines for lic2020 (http://lic2020.cipsc.org.cn/)☆218Updated 4 years ago
- Bert中文文本分类☆40Updated 5 years ago
- 达观算法比赛ner任务,从重新训练bert,到finetune预测。☆75Updated 2 years ago
- 微调预训练语言模型(BERT、Roberta、XLBert等),用于计算两个文本之间的相似度(通过句子对分类任务转换),适用于中文文本☆89Updated 4 years ago
- 在bert模型的pre_training基础上进行text_cnn文本分类☆78Updated 4 years ago
- bert4keras NER☆26Updated 5 years ago
- 实现了一下multi-head-selection联合关系实体抽取☆30Updated 5 years ago
- 实体链接demo☆64Updated 5 years ago
- 法研杯2019 阅读理解赛道 top3☆150Updated last year
- 使用BERT做文本相似度☆64Updated 5 years ago
- pytorch implementation of multi-label text classification, includes kinds of models and pretrained. Especially for Chinese preprocessing.☆75Updated 5 years ago
- 限定领域的三元组抽取的一次尝试,本文将会介绍笔者在2019语言与智能技术竞赛的三元组抽取比赛方面的一次尝试。☆133Updated last year
- 微调预训练语言模型,解决多标签分类任务(可加载BERT、Roberta、Bert-wwm以及albert等知名开源tf格式的模型)☆139Updated 4 years ago
- 中国法研杯CAIL2019要素抽取任务第三名方案分享☆139Updated 4 years ago
- 事件抽取相关算法汇总☆124Updated 5 years ago
- TF-IDF+Word2vec做文本相似度计算,最好是长文本☆24Updated 5 years ago
- baidu aistudio event extraction competition☆224Updated last year
- NER(命名实体识别)中文语料,一站式获取☆129Updated 5 years ago
- code for ACL2020:《FLAT: Chinese NER Using Flat-Lattice Transformer》 我注释&修改&添加了部分源码,使得大家更容易复现这个代码。☆56Updated 4 years ago
- ccks_2019_百度实体链接技术比赛_第一名解决方案☆57Updated 5 years ago
- datagrand 2019 information extraction competition rank9☆130Updated 5 years ago
- Use deep models including BiLSTM, ABCNN, ESIM, RE2, BERT, etc. and evaluate on 5 Chinese NLP datasets: LCQMC, BQ Corpus, ChineseSTS, OCN…☆76Updated 2 years ago
- ☆38Updated 5 years ago
- 基于轻量级的albert实现albert+BiLstm+CRF☆88Updated last year