NLPJob

标签热度

机器学习 coursera 斯坦福大学 公开课 斯坦福 深度学习 自然语言处理 python 数据科学 andrew ng 数学 nlp 数据分析 数据挖掘 神经网络 大数据 计算机科学 英语 算法 deep learning 统计学 课件 数据可视化 机器学习公开课 机器学习笔记 google 机器学习视频 计算机 商业 推荐系统 数据结构 r语言 java 密码学 udacity 金融 免费电子书 电子书 公开课笔记 计算机视觉 商务英语 学术英语 python数据可视化 机器学习课程 机器人 ted 文本挖掘 r 视频 领导力 java编程 回归模型 excel 深度学习课程 mysql cousera公开课 统计 大数据公开课 ted公开课 ted演讲 线性回归 javascript mit 概率图模型 金融市场 tensorflow 学习英语 物联网 大数据专项课程 python入门 大数据课程 英语写作 英语学习 算法课程 强化学习 高级机器学习 kaggle 文本分析 机器学习资料 函数式编程 scala 游戏设计 cousera 机器学习系统 机器人公开课 开源代码 人工智能 普林斯顿大学 machine learning 线性代数 代价函数 软件工程 伯克利 管理 市场营销 财务会计 沃顿商学院 网页开发 网站开发 web开发 网络安全 python数据科学 商业分析 非对称密码学 对称密码学 应用密码学 大规模数据科学 英语听说 概率 机器学习基石 python机器学习 算法公开课 源代码 数学思维 社交网络分析 微积分公开课 杜克大学 机器学习公开课视频 公开课视频 coursera公开课视频 coursera公开课 贝叶斯 信息论 离散数学 宾夕法尼亚大学 neural networks 伯克利大学 密歇根大学 成本函数 梯度下降 云计算 编译器 自动机 cs101 daphne koller spark 软件 会计 英语交流 商业策略 风险管理 资产管理 地理信息系统 gis 卷积神经网络 面向对象编程 序列模型 移动应用开发 数据库 计算机通信 敏捷开发 高级商务分析 商务分析 商务英语课程 c语言 c++ 数据管理 投资 计算原理 计算基础 推荐系统导论 学术英语写作 android应用开发 android开发 android 机器人课程 机器人学 数据科学竞赛 yandex 深度学习公开课 深度学习书籍 数据集 机器学习资源 分布式 微积分 大规模机器学习系统 统计推断 数据科学公开课 游戏 数学思维公开课 机器学习课件 数学公开课 微积分公开课视频 微积分公开课下载 mit微积分 mit公开课 龙星计划 神经网络公开课 coursera视频 斯坦福公开课 windows ios udacity公开课 无人驾驶汽车 人机交互公开课 人机交互 正则化 过拟合 逻辑回归 模型思维 网易公开课 acl net 逻辑 cmu 情感分析 我爱公开课 引言 普林斯顿 经济 saas 52opencourse 逻辑导引 图模型 chirs manning dan jurafsky ppt 编码 时间序列 go语言课程 go语言 工程师 语法 区块链基础 区块链 网页设计 软件开发 商务基础 运营管理 商务 机器学习实战 数据系统 投资管理 swift 计算机安全与系统管理 系统管理 计算机安全 seo策略 seo工具 seo 组织领导力 css3 html5 会计基础 c sharp 英语沟通 并发 并行 全栈开发 数据仓库 商业智能 投资策略 金融基础 数据工程 python零基础 安全系统 现代密码学 硬件安全 软件安全 网络安全基础 递归神经网络 信息检索 云计算网络 云计算应用 云计算基础 云计算概念 分组交换网络 局域网 创意写作 写作 数学基础 台湾大学 基因序列 生物信息学 斯坦福算法课程 软件架构 软件设计 java程序设计 r语言基础 图论 组合数学 python数据表示 python基础 深度学习专项课程 游戏设计与开发 游戏开发 游戏设计概念 游戏设计艺术 angular 恐龙古生物学 恐龙 古生物学 推荐系统评价 jquery 英语语法 c# 高级算法 算法专项 iot python专项课程 python入门课程 商务英语交流技巧 商务英语交流 python社交网络分析 python文本挖掘 机器学习专项 金融价值 金融决策 金融公开课 数据结构与算法 大数据机器学习 大数据分析 商业与金融建模 金融建模 学术英语听说 数据分析工具 编程入门 编程 编程基础 算法思维 计算机基础 秘钥管理 hdfs 数据工程师 hive 3d交互设计 3d建模 虚拟现实 vr 洛桑联邦理工学院 函数式编程入门 数据科学课程 数据科学专项课程 学术英语课程 学术英语写作课程 斯坦福算法专项课程 斯坦福算法 python数据分析 英文简历 英文面试 英文写作 贝叶斯方法 商业分析技术 大数据建模 数据获取 数据清洗 文本挖掘课程 聚类分析 python公开课 python课程 主成分分析 深度学习资料 词意消歧 词义消歧 推荐系统入门 python书籍 机器学习算法 数据结构课程 图像处理 贝叶斯方法实战 深度学习源代码 sibyl p2p 机器学习书籍 数据结构资料 凸优化 推荐系统入门资料 数据科学导论 可视化 机器学习开源工具包 jane mcgonigal 公开课社区 挖课 courseminer 文本情感分析 多变量微积分 社会计算 数学分析公开课 概率图模型公开课 百度 吴恩达 香港科技大学 函数式语言 scala公开课 class2go coursera无法连接 coursera打不开 keith devlin 数学思维简介 社交网络 余凯 张潼 机器人视频 robert sedgewick 算法上 多伦多大学 莱斯大学 华盛顿大学 佐治亚理工学院 神经网络视频

Text Summarization

Keyword Extraction

Text Processing

Word Similarity

Best Coursera Course

+6 投票

2012年5月16日,Google发布了一项名为“知识图谱(Knowledge Graph)”的新一代“智能”搜索功能

这种搜索模式,在Google传统搜索列表右侧,添加了与搜索关键词相关的人物、地点和事物相关的事实,即 “知识图谱”。相比传统搜索结果页这种搜索模式下的搜索页面,并不与Google用户进行搜索的关键词直接匹配,而是提供与词汇所描述的“实体”或概念匹 配的页面。例如,搜索“Taj Mahal”,传统的搜索会试着通过关键词匹配Google 抓取下来的巨大网页库,找出最合适的结果,并进行排序,但在 Google Knowledge Graph 里 “Taj Mahal" 会被理解成一个实体,并在搜索结果的右侧显示它的一些基本资料,像是地理位置、Wiki 的摘要、高度、建筑师等等,再加上一些和它类似的实体,如“Great Wall of China”等。

当然,Google 也了解“Taj Mahal”不见得一定是指泰姬陵——这就是 Knowledge Graph 的威力显现出来的时候了,解决多义/歧义问题。在泰姬陵的框框底下还有两个常见的“Taj Mahal”,一个是歌手,另一个是度假村,正常状况下你如果想找这两个“Taj Mahal”,却打不对关键字的话,有可能搜索结果会被最有名的那个淹没,但 Google Knowldge Graph 可以协助你找到你要的特定的内容。

Knowledge Graph宣称努力做好三件事情。第一是让用户能够更精确地“描述”他们寻找的内容。Knowledge Graph会提供大量的搜索内容相关信息供用户筛选,这样他们能够更进一步地准确表达自己想找的内容;第二是支持和深化用户的兴趣和偏好,在给出的搜索结果里,可能潜藏着意想不到的内容,而这些让人注意的条目,一定会令人满意和惊喜;第三是话题性,希望用户 能够参与到话题内容和深度的拓展上。

Google 宣称Knonledge Graph现有数据库已经有5亿多个事物,不同事物之间的关系超过35亿条。由于在结果展示时按照用户搜索热度对实体关系进行排序,并且通过“Report a problem”和“Feedback”等功能吸引用户参与进来,对知识库质量进行评估和校正,所以用户搜索次数越多,范围越广,参与程度越高,Google 就能获取越多信息和内容,并将其补充到 Knowledge Graph 中去,在这样一个良性循环中,Google 和用户实为互惠互利。

Knowledge Graph数据源主要包括:

  • online resources like Wikipedia
  • subject-specific resources like Weather Underground for weather information and the World Bank for economic statistics
  • publicly available data from Freebase.com, a free and open database of over 24 million things, including movies, books, TV shows, celebrities, locations, companies, and more
  • Google search data (used to measure the popularity of a subject and help decide what information people most want to see)

与之类似的还有微软的Satori,二者都努力实现字符串的语义匹配。它们通过提取出网页中的非结构化数据,创造一个互联网“名词”——人、位置、物及彼此关系——的结构性数据库,它们正部分实现雅虎研究院研究人员在2009年的一篇论文《A Web of Concepts》中提出的设想,论文定义了创造真正语义Web的三大关键要素:信息提取,链接和分析。微软和Google刚刚开始融入语义的 力量:Satori包含了4亿多实体,而Knowledge Graph达到了5亿,而这些都只是整个互联网的沧海一粟。

另外,很遗憾,目前Knowledge Graph只适用于在“Google.com”进行英文语言的检索,由于中文结构化知识库资源匮乏,估计近期很难提供中文服务。

以下内容转自Google Office Blog,对Knowledge Graph有较为系统、详尽的介绍。

===============================================================

Introducing the Knowledge Graph: things, not strings

Search is a lot about discovery—the basic human need to learn and broaden your horizons. But searching still requires a lot of hard work by you, the user. So today I’m really excited to launch the Knowledge Graph, which will help you discover new information quickly and easily.

Take a query like [taj mahal]. For more than four decades, search has essentially been about matching keywords to queries. To a search engine the words [taj mahal] have been just that—two words.

But we all know that [taj mahal] has a much richer meaning. You might think of one of the world’s most beautiful monuments, or a Grammy Award-winning musician, or possibly even a casino in Atlantic City, NJ. Or, depending on when you last ate, the nearest Indian restaurant. It’s why we’ve been working on an intelligent model—in geek-speak, a “graph”—that understands real-world entities and their relationships to one another: things, not strings.

The Knowledge Graph enables you to search for things, people or places that Google knows about—landmarks, celebrities, cities, sports teams, buildings, geographical features, movies, celestial objects, works of art and more—and instantly get information that’s relevant to your query. This is a critical first step towards building the next generation of search, which taps into the collective intelligence(集体智慧) of the web and understands the world a bit more like people do.

Google’s Knowledge Graph isn’t just rooted in public sources such as Freebase, Wikipedia and the CIA World Factbook. It’s also augmented at a much larger scale—because we’re focused on comprehensive breadth and depth. It currently contains more than 500 million objects, as well as more than 3.5 billion facts about and relationships between these different objects. And it’s tuned based on what people search for, and what we find out on the web.

The Knowledge Graph enhances Google Search in three main ways to start:

1. Find the right thing
Language can be ambiguous—do you mean Taj Mahal the monument, or Taj Mahal the musician? Now Google understands the difference, and can narrow your search results just to the one you mean—just click on one of the links to see that particular slice of results:

This is one way the Knowledge Graph makes Google Search more intelligent—your results are more relevant because we understand these entities, and the nuances in their meaning, the way you do.

2. Get the best summary
With the Knowledge Graph, Google can better understand your query, so we can summarize relevant content around that topic, including key facts you’re likely to need for that particular thing. For example, if you’re looking for Marie Curie, you’ll see when she was born and died, but you’ll also get details on her education and scientific discoveries:

How do we know which facts are most likely to be needed for each item? For that, we go back to our users and study in aggregate what they’ve been asking Google about each item. For example, people are interested in knowing what books Charles Dickens wrote, whereas they’re less interested in what books Frank Lloyd Wright wrote, and more in what buildings he designed.

The Knowledge Graph also helps us understand the relationships between things. Marie Curie is a person in the Knowledge Graph, and she had two children, one of whom also won a Nobel Prize, as well as a husband, Pierre Curie, who claimed a third Nobel Prize for the family. All of these are linked in our graph. It’s not just a catalog of objects; it also models all these inter-relationships. It’s the intelligence between these different entities that’s the key.

3. Go deeper and broader
Finally, the part that’s the most fun of all—the Knowledge Graph can help you make some unexpected discoveries. You might learn a new fact or new connection that prompts a whole new line of inquiry. Do you know where Matt Groening, the creator of the Simpsons (one of my all-time favorite shows), got the idea for Homer, Marge and Lisa’s names? It’s a bit of a surprise:

 

 

We’ve always believed that the perfect search engine should understand exactly what you mean and give you back exactly what you want. And we can now sometimes help answer your next question before you’ve asked it, because the facts we show are informed by what other people have searched for. For example, the information we show for Tom Cruise answers 37 percent of next queries that people ask about him. In fact, some of the most serendipitous discoveries I’ve made using the Knowledge Graph are through the magical “People also search for” feature. One of my favorite books is The White Tiger, the debut novel by Aravind Adiga, which won the prestigious Man Booker Prize. Using the Knowledge Graph, I discovered three other books that had won the same prize and one that won the Pulitzer. I can tell you, this suggestion was spot on!

We’ve begun to gradually roll out this view of the Knowledge Graph to U.S. English users. It’s also going to be available on smartphones and tablets—read more about how we’ve tailored this to mobile devices. And watch our video (also available on our site about the Knowledge Graph) that gives a deeper dive into the details and technology, in the words of people who've worked on this project.

 

We hope this added intelligence will give you a more complete picture of your interest, provide smarter search results, and pique your curiosity on new topics. We’re proud of our first baby step—the Knowledge Graph—which will enable us to make search more intelligent, moving us closer to the "Star Trek computer(星际迷航计算机)" that I've always dreamt of building. Enjoy your lifelong journey of discovery, made easier by Google Search, so you can spend less time searching and more time doing what you love.

 

===============================================================

When you search on Google for a person, place, or thing, you might see a section to the right of your search results that highlights facts, photos, and other snippets of information about your search. Use this section to find quick information and facts about the subject or to start exploring related subjects.

To give it a try, search for your favorite movie, landmark, historical figure, or try one of these: [ Eiffel Tower ], [ Wayne's World ], [ dalmatian ], [ Galileo ]. You can also search by image to see this section of facts and information.

What you'll see

In the right-hand section, you might find a short description, image, list of facts, location map, and links to similar searches. For question-related searches like [ tallest building in the world ], you can also see the answer right there on the search page.

Here are some of the types of information that you might see:

  • Descriptions and facts that are publicly available on the Web
  • Images from the Web that are selected as the highest ranking images about the subject
  • Related searches to help you explore similar subjects, such as other Paris monuments when you search for the Eiffel Tower
  • Other information that's related to the subject, such as a map of a location, upcoming events for an artist or venue, and the latest Google+ posts for some people

For now, this section of information appears only for certain types of searches about a person, place, or thing. For example, while you won't see it appear for searches on companies, video games, and cars, you can often see it for searches about a book, movie, sports team, location, dog breed, roller coaster, or famous person.

When you search, our system considers the top search results and the content that's found in each of those webpages. If many of the top results appear to have a specific theme in common, we'll show a summary of information about that shared subject. In cases such as [ Cinderella ], you might see a few options appear in the summary box to help narrow down your search, such as when you search for the name of a book that's also a movie.

See these quick facts on on the go too! Information about people, places, or things can also been seen on Google from your tablet and smart phone devices.

Data from the Knowledge Graph

The information shown in this section comes from what we call the Knowledge Graph, a massive collection of information about real-world things and their connections to other things. The graph gathers information about a person, place, or thing from many sources, then refines the resulting information based on the most popular questions people ask about that subject.

Here are just some of the sources for this web of information:

  • online resources like Wikipedia
  • subject-specific resources like Weather Underground for weather information and the World Bank for economic statistics
  • publicly available data from Freebase.com, a free and open database of over 24 million things, including movies, books, TV shows, celebrities, locations, companies, and more
  • Google search data (used to measure the popularity of a subject and help decide what information people most want to see)

Provide feedback

The information in these sections is compiled by automated systems, so there's always a chance that some of the information is incorrect or no longer relevant. If you see any issues, just click the "Report a problem" link at the bottom of the box and identify the piece of content in question.

We'll incorporate your feedback to help improve the content in the future. In the meantime, know that the information you see changes naturally over time just as search results do.

 

分类:信息抽取 | 用户: (2.4k 分)
修改于 用户:

 

来自@唐杰THU :

写了一个关于Knowledge Graph的简介。概念2001年Tim已经提出,10多年后Google开始真的大规模使用,Bing和Facebook也紧随其后, @搜狗搜索 的知立方算是国内代表了,@王海勋haixun的probase也很猛。另外列出几个开源库,DBPedia、Wikilinks、Freebase、Data.gov、Wolframalpha。

http://photo.weibo.com/2126427211/wbphotos/large/photo_id/3561549094028015?refer=weibofeedv5

登录 或者 注册 后回答这个问题。

...