sunnymarkliu Goto Github PK

document-qa

dssm-lstm

The LSTM-DSSM model refering to the paper: Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval

dtn-tensorflow

domain transfer network. tensorflow implementation of unsupervised cross-domain image generation

dureader

Baseline Systems of DuReader Dataset

dureader-bert

try to apply bert on Dureader

dureader-bert-1

BERT Dureader阅读理解 排名第七

eda_nlp_for_chinese

An implement of the paper of EDA for Chinese corpus.中文语料的EDA数据增强工具。NLP数据增强。论文阅读笔记。

ekphrasis

Collection of lightweight text processing tools, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting hashtags) and spell correction, using word statistics from 2 big corpora (english Wikipedia, twitter - 330mil english tweets).

elmoformanylangs

Pre-trained ELMo Representations for Many Languages

embedkgqa

ACL 2020: Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings

entity-relation-as-multi-turn-qa

Code for ACL 2019 : Entity-Relation Extraction as Multi-Turn Question Answering

entity-relation-extraction

Entity and Relation Extraction Based on TensorFlow and BERT. 基于TensorFlow和BERT的管道式实体及关系抽取，2019语言与智能技术竞赛信息抽取任务解决方案。Schema based Knowledge Extraction, SKE 2019

es6tutorial

《ECMAScript 6入门》是一本开源的JavaScript语言教程，全面介绍ECMAScript 6新增的语法特性。

face_recognition

使用webface人脸数据集以及DeepID网络，通过Caffe训练出模型参数，得到LFW二分类的人脸识别准确率。

fast-neural-style-tensorflow

A tensorflow implementation for fast neural style!

fasttext

Library for fast text representation and classification.

feature-engineering-for-ml-zh

:book: [译] 面向机器学习的特征工程

feature-selection

Features selection algorithm based on self selected algorithm, loss function and validation method

fks

前端技能汇总 Frontend Knowledge Structure

fru

fully-differentiable-deep-ndf-tf

Fully differentiable deep-neural decision forest in tensorflow

funcat

Funcat 将同花顺、通达信、文华财经麦语言等的公式写法移植到了 Python 中。

g-reader

2018年机器阅读理解技术竞赛模型，国内外1000多支队伍中BLEU-4评分排名第6， ROUGE-L评分排名第14。（未ensemble，未嵌入训练好的词向量，无dropout）

gecco

易用的轻量化的网络爬虫(Easy to use lightweight web crawler)，直接将各种格式的内容抓取并结构化为java bean

giveme5w1h

Extraction of the journalistic five W and one H questions (5W1H) from news articles: who did what, when, where, why, and how?

google-interview-university

A complete computer science study plan to become a software engineer.

hanzi_char_featurizer

汉字字符特征提取器 (featurizer)，提取汉字的特征（发音特征、字形特征）用做深度学习的特征

hosts

:statue_of_liberty:最新可用的google hosts文件。镜像：

information-extraction-chinese

Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取

instacart-basket-prediction

Kaggle | Instacart Market Basket Analysis🥕🥉