- 南大软院842复习 15
- 分词 1
- leetcode刷题笔记 62
- python学习 11
- 机器学习 22
- 《利用python进行数据分析第二版》读书笔记 8
- 学术研究 4
- 编程之法刷题笔记 12
- 图像处理 3
- OCR 19
- 文献阅读 50
- 环境工具安装 18
- Linux 5
- 依存句法分析 1
- 语义角色标注 1
- 工程 2
- 实习 10
- 基础算法 1
- 工作 4
- 牛客 3
- NLP 2
- 文本纠错 6
- 环境工具 1
南大软院842复习
- 842经典真题
- 计算机网络
- 最后冲刺
- 842数据结构复习之递归算法
- 842数据结构复习之算法策略
- 842数据结构复习之数据类型
- 842数据结构复习之基本算法
- 842数据结构复习之算法分析
- 842软工复习4(详细设计的设计模式)
- 842软工复习3(详细设计中的面向对象方法下的信息隐藏)
- 842软工复习2(详细设计中的面向对象方法下的模块化)
- 842软工复习1
- 842操作系统复习2
- 842操作系统复习
- 842复习重点概要
分词
leetcode刷题笔记
- 647. Palindromic Substrings
- 983. Minimum Cost For Tickets
- 70. Climbing Stairs
- 931. Minimum Falling Path Sum
- 877. Stone Game
- 338. Counting Bits
- 1025. Divisor Game
- 746. Min Cost Climbing Stairs.md
- 303. Range Sum Query - Immutable
- 303. Range Sum Query - Immutable
- 521. Longest Uncommon Subsequence I
- 409. Longest Palindrome.md
- 378. Kth Smallest Element in a Sorted Matrix
- 232. Implement Queue using Stacks
- 1. Two Sum
- 160. Intersection of Two Linked Lists
- 241. Different Ways to Add Parentheses
- 69. Sqrt(x)
- 309. Best Time to Buy and Sell Stock with Cooldow
- 463. Island Perimeter
- 459. Repeated Substring Pattern
- 455. Assign Cookies
- 347. Top K Frequent Elements
- 215. Kth Largest Element in an Array
- 75. Sort Colors
- 447. Number of Boomerangs
- 448. Find All Numbers Disappeared in an Array
- 167. Two Sum II - Input array is sorted
- 434. Number of Segments in a String
- 119. Pascal's Triangle II
- 3. Longest Substring Without Repeating Characters
- 206. Reverse Linked List
- 198. House Robber
- 160. Intersection of Two Linked Lists
- 204. Count Primes
- 202. Happy Number
- 191. Number of 1 Bits
- 217. Contains Duplicate
- 190. Reverse Bits
- 172. Factorial Trailing Zeroes.py
- 171. Excel Sheet Column Number
- 155. Min Stack
- 141. Linked List Cycle
- 136. Single Number.py
- 122. Best Time to Buy and Sell Stock II
- 121. Best Time to Buy and Sell Stock
- 118. Pascal's Triangle
- 344. Reverse String
- 242. Valid Anagram
- 237. Delete Node in a Linked List
- 387. First Unique Character in a String
- 371. sum of two integers
- 268. missing number
- 125. valid palindrome
- 412. fizz buzz
- 169. majority element
- 350. intersection of two arrays ii
- 326. power of three
- 283. move zeroes
- 234. palindrome linked list
- 108. convert sorted array to binary search tree
- 107 binary tree level order traversal ii
python学习
- python表格
- python元组
- python词典
- python json
- python正则表达式
- python文件操作
- python文件操作
- python面向对象
- python函数
- python字符串
- python基础语法
机器学习
- SIF句向量
- seq2seq
- pointer网络
- mnist分类
- CS224n作业
- transformer
- BERT
- 机器学习基础
- attention
- word2vec
- RNN
- 2018-11-15-CRNN
- kaggle比赛入门
- Tensorflow
- Tensorboard
- CNN
- 2018-09-18-softmax
- 2018-08-01-逻辑回归
- 2018-07-30-多元回归问题
- 2018-07-26-回归问题
- 2018-07-17-梯度高级优化Octave实现
- octave入门
《利用python进行数据分析第二版》读书笔记
- 第8章 数据规整：聚合、合并和重塑
- 第7章 数据清洗和准备
- 第6章 数据加载、存储与文件格式
- 第5章 pandas入门
- 第3章 Python的数据结构、函数和文件
- 第4章 numpy基础
- 第一章 准备工作
- 第2章 Python语法基础
学术研究
编程之法刷题笔记
图像处理
OCR
- OCR数据集
- 编辑距离
- 百度API使用
- 标题分类_OCR
- OCR系统使用
- tesseract使用
- OCR项目说明
- 轮廓处理
- 霍夫变换
- 二值化
- 表格处理
- 字符模板匹配
- 检查点
- 图片的腐蚀以及膨胀
- OCR调研
- CNN单字模型预测
- 投影直方图+图片二值化+颜色空间转换
- pdf转img
- 数据生成
文献阅读
- Overview of SIGHAN 2014 Bake-off for Chinese Spelling Check
- Deep Recurrent Generative Decoder for Abstractive Text Summarization
- Hybrid Attention for Chinese Character-Level Neural Machine Translation
- Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
- Confusionset-guided Pointer Networks for Chinese Spelling Check
- Automatic Spelling Correction for Resource-Scarce Languages using Deep Learning
- Adapting sequence models for sentence correction
- A multilayer convolutional encoder-decoder neural network for grammatical error correction
- A New Benchmark and Evaluation Schema for Chinese Typo Detection and Correction
- A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check
- Multi-headed Architecture Based on BERT for Grammatical Errors Correction
- Semi-Supervised Sequence Modeling with Cross-View Training
- Linguistically-Informed Self-Attention for Semantic Role Labeling
- ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views
- Automatic Error Checking and Correction of Electronic Medical Records
- OCR of Historical Printings of Latin Texts: Problems, Prospects, Progress
- Unsupervised profiling of OCRed historical documents[B刊]
- Learning string distance with smoothing for OCR spelling correction【C刊】
- Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised Sanskrit
- Adaptive Edit-Distance and Regression Approach for Post-OCR Text Correction
- PoCoTo - an open source system for efficient interactive postcorrection of OCRed historical texts
- [开源期刊C以下]Deep Learning-Aided OCR Techniques for Chinese Uppercase Characters in the Application of Internet of Things
- [C刊]Web Knowledge Base Improved OCR Correction for Chinese Business Cards
- [C刊]Improving OCR Accuracy on Early Printed Books by Utilizing Cross Fold Training and Voting DAS 2018: 423-428
- Attention Strategies for Multi-Source Sequence-to-Sequence Learning
- Commonsense for Generative Multi-Hop Question Answering Tasks
- Correction of OCR Word Segmentation Errors in Articles from the ACL Collection through Neural Machine Translation Methods
- Statistical learning for OCR error correction
- A novel Arabic OCR post-processing using rule-based and word context techniques. IJDAR
- Enhancing RNN Based OCR by Transductive Transfer Learning From Text to Images
- [B会]Improving OCR Accuracy on Early Printed Books by Utilizing Cross Fold Training and Voting. DAS 2018
- Post-correction of OCR Errors Using PyEnchant Spelling Suggestions Selected Through a Modified Needleman-Wunsch Algorithm
- Evaluating the Impact of OCR Errors on Topic Modeling. ICADL 2018
- Multi-Input Attention for Unsupervised OCR Correction
- 复杂表格文档预处理与文本提取算法研究
- Comparing Machine Learning Approaches for Table Recognition in Historical Register Books
- Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks
- Table Recognition in Spreadsheets via a Graph Representation
- Building fast and compact convolutional neural networks for offline handwritten Chinese character recognition
- Total-text: A comprehensive dataset for scene text detection and recognition.
- An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
- Table Recognition in Heterogeneous Documents Using Machine Learning
- Signal Processing and Communications Applications Conference
- Recognition of Table Images Using K Nearest Neighbors and Convolutional Neural Networks
- A knowledge-based table recognition method for Chinese bank statement images
- Configurable Table Structure Recognition in Untagged PDF documents
- Fast CNN-based document layout analysis
- Fast CNN-based document layout analysis
- Detecting Text in Natural Image with Connectionist Text Proposal Network
- Correcting Image Orientation Using Convolutional Neural Networks
环境工具安装
- 论文查重
- mac下tesseract安装和使用
- homebrew安装
- conda安装pytorch
- office相关操作
- conda&pip安装常见问题
- Karabiner-Elements
- kenlm使用
- macOS系统下安装虚拟机
- mac快捷键使用
- 快捷键使用
- Latex安装使用
- gitPic安装
- gensim安装
- ubuntu16.04安装Inellij idea
- ubuntu16.04设置静态ip
- 安装windows,ubuntu系统
- ubuntu16.04+pycharm+anaconda3+tensorflow+pycharm中git配置安装配置