yuye2133's repositories
Abstractive-Text-Summarization
Contrastive Attention Mechanism for Abstractive Text Summarization
ASRT_SpeechRecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
bazel
a fast, scalable, multi-language and extensible build system
bert
TensorFlow code and pre-trained models for BERT
Chinese-NewWordRecognition
专业领域词库构建/中文新词发现/专业词库发现
chinese-poetry
最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。
ChineseNER
中文命名实体识别，实体抽取，tensorflow，pytorch，BiLSTM+CRF
chip2018
chip2018
CHIP2018-1
CHIP2018问句匹配大赛 Rank6解决方案
chip2018_task2_question_pairs_matching
CHIP2018评测任务2，平安医疗科技智能患者健康咨询问句匹配大赛baseline，BiLSTM+特征工程计算相似性，10折交叉验证平均投票做bagging，F1值0.83左右，rank16。
Closer
2nd place solution to CIKM AnalytiCup 2018, determining the short-text semantic similarity.
conlleval
conlleval in Python (script for chunking/NER evaluation)
CONLP
一个自然语言处理初学者可以参考的库，包含分词，词性标注，命名实体识别，依存句法分析大多模型和算法都是自己实现 。a natural language processing library for beginners
EGPapers
事件知识图谱构建相关的论文, 包含事件抽取、事件关系识别等任务
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Fuck-XueXiQiangGuo
学习强国 懒人刷分工具 自动学习
gpt-3
GPT-3: Language Models are Few-Shot Learners
helloworld
first project in github
maccms10
苹果cms-v10,maccms-v10,开源CMS,内容管理系统,视频分享程序,分集剧情程序,网址导航程序,新闻程序,漫画程序,图片程序
NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
nlp_corpus
本人项目进行中搜集的数据集，包含原始数据和经过处理后的数据，项目持续更新。
NLPGNN
1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and GraphSAGE based on message passing.
Pre-modern_Chinese_corpus_dataset
一个近代汉语语料库数据集 This is a pre-modern Chinese ( From Song dynasty in 10th century AD to Republic of China in the early 20th Century ) language corpus.These language resources are all txt format,arranged by Dynasty（Song,Yuan,Ming,Early-Qing,Late-Qing and Republic of China）.The relevant authors' information and types of literature also have been labelled.
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.
tensorflow_poems
中文古诗自动作诗机器人，屌炸天，基于tensorflow1.10 api，正在积极维护升级中，快star，保持更新！
TextMatch
基于Pytorch的，中文语义相似度匹配模型（ABCNN、Albert、Bert、BIMPM、DecomposableAttention、DistilBert、ESIM、RE2、Roberta、SiaGRU、XlNet）
WikiSQL
A large annotated semantic parsing corpus for developing natural language interfaces.