xiao-ka's repositories
BJTUNLP_Practice2021
This is the third version of the practices for the rookies of BJTUNLPers.
NLP_Applications
nlp tasks
GloVe
GloVe model for distributed word representation
BERT-NER-Pytorch
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
chineseocr_lite
超轻量级中文ocr,支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M
Dataset
Dataset for all
nltk_data
NLTK Data
keras-yolo3
A Keras implementation of YOLOv3 (Tensorflow backend)
AntSpider
1000万豆瓣电影/评论/名人/评分数据采集源码分享(内含千万电影数据集,可下载)
C-CNN-for-Chinese-Sentiment-Analysis
基于字符级卷积神经网络的细粒度的中文情感分析以及具体的应用,将顾客打分和评论情感进行两极映射,使用数据自动标注和基于弱监督预训练的数据增强方式自动扩充和优化数据集,实验证实了在情感分类中,使用本文的字符级卷积神经网络(C-CNN-SA)可以在不依赖分词的情况下,达到的精度和 F 值均高于词级粒度。并将模型上线使用,利用tensoflow+flask restful做出的后端服务化,具体的项目细节和讲解看右面的ppt
dali
Domain Adaptation of Neural Machine Translation by Lexicon Induction
NLPBeginner
主要介绍了NLP的基础模型以及相关算法
CHINESE-OCR
[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别
SLAM-ransac
RANSAC Eliminates Mismatch (Python Implementation)
VisualOdometry_BasedOnSURF
%% Estimating the pose of the second view relative to the first view %% Bootstrapping estimating camera trajectory using global bundle adjustment %% Estimating remaining camera trajectory using windowed bundle adjustment
TOP250movie_douban
TOP250豆瓣电影短评:Scrapy 爬虫+数据清理/分析+构建中文文本情感分析模型
cMedQA2
This is updated version of the dataset for Chinese community medical question answering.
Text-Similarity
Text-Similarity Method in Pytorch
AMTTL
Code & Data for our COLING 2018 paper "Adaptive Multi-Task Transfer Learning for Chinese Word Segmentation in Medical Text"
tsp
图解遗传算法求解TSP
TSP-genetic-algorithm
An implementation of TSP by Genetic Algorithm in Java.采用遗传算法解决TSP旅行商问题的Java版程序。
vLSH
Locality Sensitive Hashing matlab toolkit
Locality-sensitive-hashing
min-hash and p-stable hash