3typicalworkonautomaticrelationextraction.pptVIP

下载本文档

0
0
约1.87千字
约 75页
2016-07-20 发布于天津
举报
版权申诉

3typicalworkonautomaticrelationextraction.ppt

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

3typicalworkonautomaticrelationextraction

3 Typical Work on Automatic Relation Extraction;Outline ;1 DIPRE: Dual Iterative Pattern Expansion;1 DIPRE: Dual Iterative Pattern Expansion;;1.2 Algorithm ;Pattern generation;1.3 Experiments;1.3 Experiments: Initial sample;1.3 Experiments: 3 Patterns in First Iteration;1.3 Experiments: 4047 new pairs in First Iteration;1.3 Experiments: review;1.4 Conclusion;Outline ;KNOWITALL;Introduction;1 Flowchart of the main components in KnowItAll;Information Focus;通用的抽取模板;Extraction Rules;Discriminator;Training discriminator: Bootstrapping;The result of training;An Example;An Example:Trained discriminator;An ExampleMain cycle: extract;An ExampleMain cycle: Assess;1.2 Experiment noise tolerance;1.2 Experiment find negative training seeds for assessor;1.2 Experiment: search cutoff metric;2 如何提高召回率;2.1 Pattern Learning (PL):; Pattern Learning algorithm; 3 of the most productive rules;如何提高召回率;2.2 Subclass ExtractionBasic subclass extraction (SEbase);Rules for subclass extraction;Improving Subclass Extraction Recall;Experimental result: Context-independent subclass;Experimental result: Context-dependent subclass;如何提高召回率;2.3 List Extractor;Learning a Wrapper;An Example;Experiments of LE;Discussion;2.4 PL，SE和LE的比较：recall;PL，SE和LE的比较: extraction rate;the Trade-off between Recall and Precision;3 Conclusion;Outline ;Open IE;1 Introduction;1.1 新的挑战;新的挑战;新的挑战;1.2 本文的贡献;2 Open IE;2.1 Self-Supervised Learner;2.1 Self-Supervised Learner;2.2 Single-Pass Extractor;2.3 Redundancy-Based Assessor;2.4 Query Processing;2.5 Analysis;3 Experimental Results: 3.1 Comparison with Traditional IE;3 Experimental Results: Comparison with Traditional IE;3 Experimental Results:3.2 Global Statistics on Facts Learned;Estimating the Correctness of Facts;;Estimating the Number of Distinct Facts;Estimating the Number of Distinct Facts;4 Conclusion;SUMMARY;SUMMARY;感谢大家！