期刊文献+

基于虚结点方法的在线实体指代项识别

ONLINE ENTITY MENTION RECOGNITION BASED ON VIRTUAL NODE
下载PDF
导出
摘要 在自然语言处理中,实体指代项识别通常被看作是序列标注任务进行处理。而实体指代项又是由多个连续的序列标注子任务组成的。这些子任务包括切分识别、实体识别和指代项识别。传统的管道方法经常会导致每步间的错误向下传递。级联方式的联合模型会带来大量的标记。虚结点方法同时规避了上面两个方法的缺点。系统采用虚结点的在线联合模型,不仅减少了训练时间,性能也比普通的在线联合模型要好。 Entity mention recognition is always processed as sequence labelling task in natural language processing and the entity mention is composed of several sequence labelling subtasks.These subtasks are segmentation recognition,entity recognition and mention recognition.Traditional pipeline approaches often lead to error downward propagation between subtasks.Joint model with cascaded structures may introduce large amounts of label.The virtual node approach avoids the two problems above.My system,using online joint model with virtual node,not only reduces the training time,but is also proved to be better than the ordinary online joint models in performance.
作者 俞一乘
出处 《计算机应用与软件》 CSCD 北大核心 2012年第4期192-194,219,共4页 Computer Applications and Software
关键词 实体指代识别 虚结点 级联 Entity mention recognition Virtual node Cascade
  • 相关文献

参考文献8

  • 1Shinyama Y,Sekine S. Named Entity Discovery Using Comparable News Articles[A].Geneva,Switzerland:ICCL,2004.848-853. 被引量:1
  • 2Settles B. Biomedical Named Entity Recognition using Conditional Random Fields and Rich Feature Sets[A].Geneva,Switzerland:ICCL,2004.107-110. 被引量:1
  • 3Shen D,Zhang J,Zhou G. Effective Adaptation of Hidden Markov Model-Based Named Entity Recognizer for Biomedical Domain[A].Budapest:ACL,2003.49-56. 被引量:1
  • 4Oliver Bender,Franz Josef Och,Hermann Ney. Maximum Entropy Models for Named Entity Recognition[A].Canada:HLT-NAACL,CONLL,2003. 被引量:1
  • 5Ng H,Low J. Chinese part of speech tagging:One-at-a-time or all-atonce wordbased or character-based[A].Barcelona,Spain:EMNLP,2004.277-284. 被引量:1
  • 6Xian Qian,Qi Zhang,Yaqian Zhou. Joint Training and Decoding Using Virtual Nodes for Cascaded Segmentation and Tagging Tasks[A].MIT,Massachusetts,USA:EMNLP,2010. 被引量:1
  • 7Michael Collins. Discriminative Training Methods for Hidden Markov Models:Theory and Experiments with Perceptron Algorithms[A].University of Pennsylvania,Philadelphia,PA,USA:EMNLP,2002. 被引量:1
  • 8Yoav Freund,Robert E.Schapire. Large Margin Classification Using the Perceptron Algorithm[A].Springer-verlag,1999.277-296. 被引量:1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部