T2：Joint Models in Natural Language Processing

摘要：自然语言处理中的很多任务包含多个步骤。比如，分词是很多中文处理任务的基础。每个步骤任务可以分别建模,形成一个多部模型。然而,多部模型具有两个缺点。首先,不同步骤之间存在错误蔓延。其次,不同步骤之间难以共享信息。联合模型可以用于解决以上问题。构造联合模型的挑战有两点。第一,不同步骤的搜索空间组合形成算法挑战。第二，不同步骤之间信息共享形成建模挑战。这次讲习班讨论联合模型用于不同自然语言处理任务,从统计模型开始,到神经原网络模型为止。基于图和基于转移的模型会被讨论。

Abstract：Many tasks in natural language processing consist of multiple steps. For example, word segmentation is a necessary first step before many subsequent tasks. Sub tasks can be modeled separately, forming a pipeline. However, this method has two limitations. First, error propagate from predecessing tasks to successing tasks. Second, information from subsequent tasks cannot be utilized by predecessing task. Joint models can be built to solve the issues above. There are two main challenges. First, combination of different tasks leads to more complex search space. Second, a model must consider information exchange between different tasks. In this tutorial, we review joint models for solving natural language processing problems, starting from statistical models and moving towards neural network methods. Both graph-based and transition-based models will be discussed. （讲义内容为英文，报告语言为中文。）

个人简介：张岳，新加坡科技设计大学助理教授。获清华大学计算机科学与技术学士学位，牛津大学计算机科学硕士和博士学位。2012年加入新加坡科技设计大学之前，曾在英国剑桥大学担任博士后研究员。对自然语言处理、机器学习和人工智能有浓厚的研究兴趣，主要从事统计句法分析、文本生成、机器翻译、情感分析和股票市场分析的研究。任ACM/IEEE TALLIP副主编及COLING 2014、NAACL 2015、EMNLP 2015、ACL 2017和EMNLP 2017的程序委员会领域主席和IALP 2017的程序委员会主席。

Brief introduction：Yue Zhang is currently an assistant professor at Singapore University of Technology and Design. Before joining SUTD in July 2012, he worked as a postdoctoral research associate in University of Cambridge, UK. Yue Zhang received his DPhil and MSc degrees from University of Oxford, UK, and his BEng degree from Tsinghua University, China. His research interests include natural language processing, machine learning and artificial Intelligence. He has been working on statistical parsing, parsing, text synthesis, machine translation, sentiment analysis and stock market analysis intensively. Yue Zhang serves as the reviewer for top journals such as Computational Linguistics, Transaction of Association of Computational Linguistics (standing review committee) and Journal of Artificial Intelligence Research. He is the associate editor for ACM Transactions on Asian and Low Resource Language Information Processing. He is also PC member for conferences such as ACL, COLING, EMNLP, NAACL, EACL, AAAI and IJCAI. He was the area chairs of COLING 2014, NAACL 2015, EMNLP 2015, ACL 2017 and EMNLP 2017. He is the TPC chair of IALP 2017.