BarryZM / dataProcessor
中英文语料数据清洗及分布式分句分词预处理工作
☆11Updated 4 years ago
Alternatives and similar repositories for dataProcessor:
Users that are interested in dataProcessor are comparing it to the libraries listed below
- 本项目由三个模块构成。意图识别:判断用户的意图是业务型还是闲聊型;模型检索:该部分构建一个语料库,当用户 发起新的query(通过意图识别判断为业务型对话)时,为用户匹配query检索的最佳response,使用HSWN进行召回(粗排), 然后构建句子的相似度,并利用Lig…☆10Updated 3 years ago
- 基于预训练模型的中文关键词抽取方法(论文SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model 的中文版代码)☆12Updated 4 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。☆37Updated 9 months ago
- 使用fastNLP架构简单利用Bert-Bi-LSTM-CRF实现中文NER☆15Updated 4 years ago
- 基于BERT+Biaffine结构的关系抽取模型☆11Updated 2 years ago
- 文言文信息抽取(实体识别+关系抽取)☆9Updated last year
- 基于文本相似度的win10智能客服问答系统☆15Updated 4 years ago
- 依存句法解析☆15Updated 4 years ago
- 基于知识图谱的QA系统,BERT模型☆18Updated 5 years ago
- ☆13Updated last year
- solve text generation tasks by the language model GPT2, including papers, code, demo demos, and hands-on tutorials. 使用语言模型GPT2来解决文本生成任务的…☆28Updated 5 years ago
- 闲聊机器人☆11Updated 4 years ago
- Code for "A Unified Model for Joint Chinese Word Segmentation and Dependency Parsing"☆38Updated 2 years ago
- 带拼音、字形特征的文本纠错模型☆11Updated 2 years ago
- flyai 医疗QA NLG☆21Updated 5 years ago
- 这是我2014级本科毕业论文项目,在深交所实习期间完成!☆19Updated 6 years ago
- bert,albert计算中文句子的相似度☆21Updated 4 years ago
- Sentence-Transformers Information Retrieval example on Chinese☆29Updated 11 months ago
- Seq2seqAttGeneration, an basic implementation of text generation that using seq2seq attention model to generate poem series. this project…☆18Updated 4 years ago
- 2020阿里云天池大数据竞赛-中医药命名实体识别挑战赛☆27Updated 4 years ago
- 基于BERT-CRF的命名实体识别模型☆14Updated 2 years ago
- 问答摘要/seq2seq/PGN/Bert_sum/UniLM☆18Updated 4 years ago
- 基于触发词的燃气事件抽取,包括:时间、地点、原因、后果、组织等实体信息☆8Updated 3 years ago
- Simple Transformers四种任务(分类、命名实体识别、机器阅读理解、语言模型微调)的代码样例,可以切换多种预训练模型。☆22Updated 2 years ago
- 用户画像,知识图谱挖掘☆10Updated 2 years ago
- 论文阅读☆21Updated 3 years ago
- 端到端的基于知识图谱的问答系统,分为实体识别和关系分类两部,在BERT基础上做多任务联合训练。☆30Updated 5 years ago
- 基于pytorch+bilstm_crf的中文命名实体识别☆14Updated 2 years ago
- Using CRF++ for NER☆20Updated 5 years ago
- sodic2021 法律咨询智能问答 Baseline 线上35+☆17Updated 3 years ago