rollben Goto Github PK

followers: 2.0 following: 21.0 repos: 57.0 gists: 0.0

Name: Zhang Junwen

Type: User

Bio: interest research erea: NLP (dialogue system, chatbot, natural Language understanding, knowledge graph) and CV

Location: Shanghai

Zhang Junwen's Projects

knowledge_grapy-kbqa_demo

将bert模型应用到问答系统中来，一者学习知识图谱的基本操作，二简单搭建问答系统的基本框架，三将词向量、bert模型实践应用

language_understanding_based_bert

基于BERT的预训练语言模型实现，分为两步：预训练和微调。目前已包括BERT、Roberta、ALbert三个模型，且皆可支持Whole Word Mask模式。

lattice-slu

Source code for ASRU 2019 paper "Adapting Pretrained Transformer to Lattices for Spoken Language Understanding"

neural-chinese-address-parsing

Neural Chinese Address Parsing

自然语言处理（nlp），小姜机器人（闲聊检索式chatbot），BERT句向量-相似度（Sentence Similarity），XLNET句向量-相似度（text xlnet embedding），文本分类（Text classification），实体提取（ner，bert+bilstm+crf），数据增强（text augment, data enhance），同义句同义词生成，句子主干提取（mainpart），中文汉语短文本相似度，文本特征工程，keras-http-service调用

pretrained-models

Open Language Pre-trained Model Zoo

pretraining-for-language-understanding

Pre-training of Language Models for Language Understanding

pyclue

Python toolkit for Chinese Language Understanding(CLUE) Evaluation benchmark

pycorrector

pycorrector is a toolkit for text error correction. It was developed to facilitate the designing, comparing, and sharing of deep text error correction models.