Probabilistic Models of Nonprojective Dependency Trees对非投射依存树的概率模型.pptVIP

下载本文档

13
0
约4.76千字
约 19页
2017-03-08 发布于上海
举报
版权申诉

Probabilistic Models of Nonprojective Dependency Trees对非投射依存树的概率模型.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

Probabilistic Models of Nonprojective Dependency Trees对非投射依存树的概率模型

28 June 2007 EMNLP-CoNLL Probabilistic Models of Nonprojective Dependency Trees David A. Smith Center for Language and Speech Processing Computer Science Dept. Johns Hopkins University See Also Nonprojective Syntax Edge-Factored Models (McDonald et al., 2005) If Only It Were Projective… Graph Theory to the Rescue! Building the Kirchoff (Laplacian) Matrix Why Should This Work? When You Have a Hammer… Analogy to Other Models More Machinery: The Gradient Nonprojective Conditional Log-Linear Training Minimum Bayes-Risk Parsing Edge Clustering Edge Clustering What’s Wrong with Edge Clustering? Constraints on Link Length Conclusions O(n3) inference for edge-factored nonprojective dependency models Performance closely comparable to MIRA Learned edge clustering doesn’t seem to help unlabeled parsing Many other applications to hit Thanks * * Noah A. Smith Language Technologies Institute Machine Learning Dept. School of Computer Science Carnegie Mellon University On the Complexity of Non-Projective Data-Driven Dependency Parsing R. McDonald and G. Satta IWPT 2007 Structured-Prediction Models via the Matrix-Tree Theorem T. Koo, A. Globerson, X. Carreras and M. Collins EMNLP-CoNLL 2007 Coming Up Next! ista meam norit gloria canitiem ROOT I give a on bootstrapping talk tomorrow ROOT ‘ll thatNOM myACC may-know gloryNOM going-grayACC How would we parse this? That glory shall last till I go gray Non-neg. score for each edge Find edge sum among legal trees children parents Score edges in isolation Find maximum spanning tree with Chu-Liu-Edmonds NP hard to add sibling or degree constraints, hidden node variables What about training? Unlabeled for now I give a on bootstrapping talk tomorrow ROOT ‘ll An Inside-Outside algorithm gives us Normalizing constant for globally normalized models Posterior probability of edges Summing over hidden variables But we can’t use Inside-Outside for nonprojective parsing! Tutte’s Matrix-Tree Theorem (1948) The determinant of the Kirchoff (aka Laplac