图 书 馆
自然语言处理中的近似推理Approximate Inference in Natural Language Processing |
|
| 课程网址: | http://videolectures.net/nipsworkshops09_smith_ainlp/ |
| 主讲教师: | Noah Smith |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2010-01-19 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | I'll start out by presenting an idealized version of the natural language processing problem of parsing. I will brazenly suggest that most of NLP is reducible to variations on parsing problems. I'll show how dynamic programming solves the idealized version of the problem, both for calculating modes and marginals over parse trees, exploiting some key independence assumptions about the structure of natural language sentences. I will then discuss two approximate inference methods that let us build more powerful models of parsing. Neither comes with strong theoretical guarantees, but both are demonstrated to perform strongly in experiments on real NLP data. The first method builds on the dynamic programming representation, combining max-product and sum-product methods to produce, approximately, the k-best parses and a residual sum over the rest of the parses, useful when incorporating features that violate the usual independence assumptions. Experiments validate the approach with a discriminative model for machine translation. The second method turns a parsing problem instance into a concise integer linear program. Approximate inference is then accomplished using well-known linear program relaxation. This is embedded in a new online learning algorithm that tries to penalize uninterpretable fractional solutions (and therefore inference cost at evaluation time). We show that this approach leads to state-of-the-art parsing performance on seven languages, with improved speed for both exact and approximate inference and no significant performance loss. |
| 关 键 词: | 自然语言; 动态编程; 积乘积方法 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-09-07：lxf |
| 阅读次数: | 76 |