All Projects → wgwang → Ccks2020 Baseline

wgwang / Ccks2020 Baseline

CCKS 2020: 基于本体的金融知识图谱自动化构建技术评测

Projects that are alternatives of or similar to Ccks2020 Baseline

Ml Dl Projects
Personal projects using machine learning and deep learning techniques
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Rl Cc
Web-based Reinforcement Learning Control Center
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Cnn graph
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Stars: ✭ 1,110 (+1719.67%)
Mutual labels:  jupyter-notebook
Instapy Research
📄 Research repository for InstaPy
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Vehicle Detection And Tracking
Udacity Self-Driving Car Engineer Nanodegree. Project: Vehicle Detection and Tracking
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Rpi Docker Tensorflow
Docker container for the Raspberry Pi containing Tensorflow and Jupyter
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Kaggle challenge live
This is the code for "Kaggle Challenge (LIVE)" by Siraj Raval on Youtube
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Kdd Multimodalities Recall
This is our solution for KDD Cup 2020. We implemented a very neat and simple neural ranking model based on siamese BERT which ranked first among the solo teams and ranked 12th among all teams on the final leaderboard.
Stars: ✭ 61 (+0%)
Mutual labels:  jupyter-notebook
Bayesian Linear Regression
A python tutorial for a Bayesian treatment of Linear Regression: https://zjost.github.io/bayesian-linear-regression/
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Insightface pytorch
Pytorch0.4.1 codes for InsightFace
Stars: ✭ 1,109 (+1718.03%)
Mutual labels:  jupyter-notebook
Cats Dogs Cortex Redux
Kaggle Cats & Dogs Redux with Cortex and Resnet50
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Embedded gcnn
Embedded Graph Convolutional Neural Networks (EGCNN) in TensorFlow
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Python4scientificcomputing fundamentals
This repository includes the guidelines and the exercise files of the first part of my lectures on python for scientific programming which is dedicated to a general introduction to Python programming language. These lectures are a part of the "Energy and Environmental Technologies for Building Systems" course offered for M.Sc in Energy Eng. at Politecnico di Milano.
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Pycon Ua 2018
Talk at PyCon UA 2018 (Kharkov, Ukraine)
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Itorch
IPython kernel for Torch with visualization and plotting
Stars: ✭ 1,110 (+1719.67%)
Mutual labels:  jupyter-notebook
Data scientist nanodegree
Stars: ✭ 59 (-3.28%)
Mutual labels:  jupyter-notebook
Data Science Cookbook
🎓 Jupyter notebooks from UFC data science course
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Rechunker
Disk-to-disk chunk transformation for chunked arrays.
Stars: ✭ 61 (+0%)
Mutual labels:  jupyter-notebook
Matplotlib Multilayer Network
small template code to create a multilayer network using matplotlib and networkx
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook
Silverhand
Micheal Gardner的数据科学笔记
Stars: ✭ 60 (-1.64%)
Mutual labels:  jupyter-notebook

CCKS 2020 Baseline: 基于本体的金融知识图谱自动化构建技术评测的指引

竞赛主页

https://www.biendata.com/competition/ccks_2020_5/

docker

提供一个打好的镜像可直接运行,见: https://hub.docker.com/repository/docker/wgwang/ccks2020-baseline/general

竞赛背景

金融研报是各类金融研究结构对宏观经济、金融、行业、产业链以及公司的研究报告。报告通常是有专业人员撰写,对宏观、行业和公司的数据信息搜集全面、研究深入,质量高,内容可靠。报告内容往往包含产业、经济、金融、政策、社会等多领域的数据与知识,是构建行业知识图谱非常关键的数据来源。另一方面,由于研报本身所容纳的数据与知识涉及面广泛,专业知识众多,不同的研究结构和专业认识对相同的内容的表达方式也会略有差异。这些特点导致了从研报自动化构建知识图谱困难重重,解决这些问题则能够极大促进自动化构建知识图谱方面的技术进步。

本评测任务参考 TAC KBP 中的 Cold Start 评测任务的方案,围绕金融研报知识图谱的自动化图谱构建所展开。评测从预定义图谱模式(Schema)和少量的种子知识图谱开始,从非结构化的文本数据中构建知识图谱。其中图谱模式包括 10 种实体类型,如机构、产品、业务、风险等;19 个实体间的关系,如(机构,生产销售,产品)、(机构,投资,机构)等;以及若干实体类型带有属性,如(机构,英文名)、(研报,评级)等。在给定图谱模式和种子知识图谱的条件下,评测内容为自动地从研报文本中抽取出符合图谱模式的实体、关系和属性值,实现金融知识图谱的自动化构建。所构建的图谱在大金融行业、监管部门、政府、行业研究机构和行业公司等应用非常广泛,如风险监测、智能投研、智能监管、智能风控等,具有巨大的学术价值和产业价值。

评测本身不限制各参赛队伍使用的模型、算法和技术。希望各参赛队伍发挥聪明才智,构建各类无监督、弱监督、远程监督、半监督等系统,迭代的实现知识图谱的自动化构建,共同促进知识图谱技术的进步。

竞赛任务

本评测任务参考 TAC KBP 中的 Cold Start 评测任务的方案,围绕金融研报知识图谱的自动化图谱构建所展开。评测从预定义图谱模式(Schema)和少量的种子知识图谱开始,从非结构化的文本数据中构建知识图谱。评测本身不限制各参赛队伍使用的模型、算法和技术。希望各参赛队伍发挥聪明才智,构建各类无监督、弱监督、远程监督、半监督等系统,迭代的实现知识图谱的自动化构建,共同促进知识图谱技术的进步。

联系

达观数据 [email protected]

参与

  • 关于baseline的任何问题可以使用issue进行交流,有任何改进的想法可以使用pr参与
  • 有任何竞赛本身的问题、想法,欢迎扫描下面二维码加入竞赛QQ群讨论
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].