图 书 馆
多面体外逼近在自然语言解析中的应用Polyhedral Outer Approximations with Application to Natural Language Parsing |
|
| 课程网址: | http://videolectures.net/icml09_martins_poaa/ |
| 主讲教师: | André F. T. Martins |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2009-09-17 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Recent approaches to learning structured predictors often require approximate inference for tractability; yet its effects on the learned model are unclear. Meanwhile, most learning algorithms act as if computational cost was constant within the model class. This paper sheds some light on the first issue by establishing risk bounds for max-margin learning with LP relaxed inference, and addresses the second issue by proposing a new paradigm that attempts to penalize "time-consuming" hypotheses. Our analysis relies on a geometric characterization of the outer polyhedra associated with the LP relaxation. We then apply these techniques to the problem of dependency parsing, for which a concise LP formulation is provided that handles non-local output features. A significant improvement is shown over arc-factored models. |
| 关 键 词: | 学习结构化; 预测变量; 新范式 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-04-24：cwx |
| 阅读次数: | 64 |