专栏名称: 机器学习研究会
机器学习研究会是北京大学大数据与机器学习创新中心旗下的学生组织,旨在构建一个机器学习从事者交流的平台。除了及时分享领域资讯外,协会还会举办各种业界巨头/学术神牛讲座、学术大牛沙龙分享会、real data 创新竞赛等活动。
目录
相关文章推荐
数据法盟  ·  孟晚舟:AI的潮水正在涌入各行各业的生产系统 ·  14 小时前  
数据法盟  ·  孟晚舟:AI的潮水正在涌入各行各业的生产系统 ·  14 小时前  
爱可可-爱生活  ·  [CL] Next Token ... ·  昨天  
爱可可-爱生活  ·  《爱可可微博热门分享(12.29)》 ... ·  2 天前  
爱可可-爱生活  ·  【Aria-UI:视觉定位GUI指令,一款能 ... ·  3 天前  
51好读  ›  专栏  ›  机器学习研究会

【课程】宾夕法尼亚大学课程:面向自然语言处理的高级机器学习技术

机器学习研究会  · 公众号  · AI  · 2017-09-04 22:10

正文



点击上方“机器学习研究会”可以订阅
摘要
 

转自:爱可可-爱生活

CIS 700: Advanced Machine Learning for Natural Language Processing

by Dan Roth

Tuesday and Thursday, 6:00-7:30 PM, 303 Towne Building




Course Description

Making decisions in natural language processing problems often involves assigning values to sets of interdependent variables where the expressive dependency structure can influence, or even dictate, what assignments are possible. Structured learning problems such as semantic role labeling provide one such example, but the setting is broader and includes a range of problems such as name entity and relation recognition and co-reference resolution. The setting is also appropriate for cases that may require a solution to make use of multiple models (possible pre-designed or pre-learned components) as in summarization, textual entailment and question answering.

This semester, we will devote the course to the study of structured learning problems in natural language processing. We will start by recalling the ``standard” learning formulations as used in NLP, move to formulations of multiclass classification and from then on focus on models of structure predictions and how they are being used in NLP.

Through lectures and paper presentations the course will introduce some of the central learning frameworks and techniques that have emerged in this area over the last few years, along with their application to multiple problems in NLP and Information Extraction. The course will cover:

Models: We will present both discriminative models such as structured Perceptron and Structured SVM, Probabilistic models, and Constrained Conditional Models.

Training Paradigms: Joint Learning models; Decoupling learning from Inference; Constrained Driven Learning; Semi-Supervised Learning of Structure; Indirect Supervision

Inference: Constrained Optimization Models, Integer Linear Programming, Approximate Inference, Dual Decomposition.

Prerequisites

Machine Learning class; CIS 419/519/520 or equivalent. Knowledge of NLP is recommended but not mandatory.

Grading and Expectations

There will be

  • Course Projects - The project will be done in teams of sizes 2 or 3; teams will proposed projects and consult us. We will have milestones along define a few intermediate stages and results will be reported and presented at the end of each stage.

  • Four reading assignments - Mandatory readings and additional recommended readings will be assigned every week.

  • A Short Critical Survey - Four (4) times a semester you will write a short critical essay on one of the additional readings.

  • Presentations - Once or twice you will present a paper from the additional readings (30 minutes, focusing on the mathematical/technical details of the paper). The presentations will be prepared in groups, whenever possible, and a group of presentations will form a coherent tutorial, whenever possible (more on that later).

There is no final exam.

Expectations

This is an advanced course. I view my role as guiding you through the material and helping you in your first steps as an researcher. I expect that your participation in class, reading assignments and presentations will reflect independence, mathematical rigor and critical thinking.


链接:

http://www.cis.upenn.edu/~danroth/Teaching/CIS-700-006/index.html


原文链接:

https://m.weibo.cn/1402400261/4148171758012672

“完整内容”请点击【阅读原文】
↓↓↓