NICE-FUTURE / three-method-to-find-synonyms
【Demo】找寻近义词的三种方法
☆26Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for three-method-to-find-synonyms
- 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☆90Updated 4 years ago
- 问题等价性判断数据预处理,包含添加对抗样本(同音字、近义词替换等)、获取样本的pattern(用通配符替换相同词汇,提取相同和不同词汇)☆39Updated 4 years ago
- Bert分类,语义相似度,获取句向量。☆64Updated last year
- 百度百科爬虫☆32Updated 5 years ago
- Label Mask for Multi-label Classification☆55Updated 3 years ago
- 基于“Seq2Seq+前缀树”的知识图谱问答☆71Updated 2 years ago
- 在bert4keras下加载CPM_LM模型☆51Updated 3 years ago
- 中文多跳问答数据集☆72Updated 6 years ago
- RelExt: A Tool for Relation Extraction from Text. 文本实体关系抽取工具。☆48Updated 2 years ago
- Sentence-Transformers Information Retrieval example on Chinese☆29Updated 8 months ago
- Dataset from 'Character-based BiLSTM-CRF Incorporating POS and Dictionaries for Chinese Opinion Target Extraction'☆41Updated 6 years ago
- 适用于常见的NLP任务的模板☆34Updated last year
- benchmark of KgCLUE, with different models and methods☆26Updated 2 years ago
- Quick run NLP in many task 快速运行分类、序列标注、匹配、生成等NLP任务的Tensorflow框架 (中文 NLP 支持分布式)☆30Updated 3 years ago
- 中文概念图谱OpenConcepts☆43Updated 2 years ago
- ☆89Updated 4 years ago
- lasertagger-chinese;lasertagger中文学习案例,案例数据,注释,shell运行☆75Updated last year
- 专业领域词库构建/中文新词发现/专业词库发现☆28Updated 4 years ago
- 基于 Tensorflow,仿 Scikit-Learn 设计的深度学习自然语言处理框架。支持 40 余种模型类,涵盖语言模型、文本分类、NER、MRC、知识蒸馏等各个领域☆114Updated last year
- Chinese Named Entity Recognition Using Neural Network☆29Updated 2 years ago
- 2020语言与智能技术竞赛:面向推荐的对话任务☆51Updated 3 years ago
- Seq2seqAttGeneration, an basic implementation of text generation that using seq2seq attention model to generate poem series. this project…☆17Updated 3 years ago
- sodic2021 法律咨询智能问答 Baseline 线上35+☆17Updated 3 years ago
- CLUEWSC2020: WSC Winograd模式挑战中文版,中文指代消解任务☆67Updated 4 years ago
- 基于BERT的无监督分词和句法分析☆110Updated 4 years ago
- SinglepassTextCluster, an TextCluster tools based on Singlepass cluster algorithm that use tfidf vector and doc2vec,which can be used for…☆62Updated 3 years ago
- 本项目使用云问科技训练的中文版UniLM模型对微博数据集进行自动标题生成。☆35Updated 7 months ago
- 格物-多语言和中文大规模预训练模型-轻量版,涵盖纯中文、知识增强、113个语种多语言,采用主流Roberta架构,适用于NLU和NLG任务, 支持pytorch、tensorflow、uer、huggingface等框架。 Multilingual and Chinese …☆25Updated last year
- transformers implement (architecture, task example, serving and more)☆97Updated 2 years ago
- Bert预训练模型fine-tune计算文本相似度☆97Updated last year