EAGER: Joint Learning for Knowledge-Rich Coreference Resolution

EAGER：联合学习以解决知识丰富的共指问题

• 批准号: 1147644
• 负责人: Vincent Ng
• 金额: $ 13万
• 依托单位: University of Texas at Dallas
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2011
• 资助国家: 美国
• 起止时间: 2011-08-15 至 2014-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1147644&HistoricalAwards=false
• 关键词: EAGER; Joint; Learning; Knowledge; Rich

This Early Grant for Exploratory Research seeks to investigate the viability of a knowledge-rich, joint-learning approach to coreference resolution, with the ultimate goal of advancing the state of the art in coreference resolution. Given recent advances in research on lexical semantics and discourse, and the development of large-scale lexical databases, the first objective of this grant is to investigate whether existing language technologies are mature enough to accurately extract semantic, discourse, and world knowledge from structured and unstructured data so that learning-based coreference systems can be significantly improved when such knowledge is employed.An assumption underlying the first objective is the use of a pipeline system architecture, where sophisticated linguistic information from various sources is computed prior to coreference resolution. While a pipeline architecture is popularly-used in coreference research, the errors made by the upstream components may propagate to the coreference component and adversely affect its performance. To address this problem, the second objective of this grant is to explore an approach in which multiple tasks in the pipeline are learned in a joint fashion. While most research on joint learning for language processing focuses on two tasks, this work seeks to take the challenge involved in joint learning to the next level by simultaneously learning a large number of tasks in semantics, discourse, and information extraction, which can all benefit from their interactions with each other and with coreference in the learning process.

这个探索性研究的早期补助金旨在研究知识丰富的联合学习方法对共指消解的可行性，最终目标是推进共指消解的最新技术水平。鉴于词汇语义和语篇研究的最新进展，以及大规模词汇数据库的发展，该资助的第一个目标是调查现有的语言技术是否足够成熟，可以准确地提取语义，语篇，以及来自结构化和非结构化数据的世界知识，当采用这种知识时，基于共指系统的共指系统可以得到显著的改进。第一个目标的基础假设是使用流水线系统架构，其中在共指消解之前计算来自各种源的复杂语言信息。流水线结构在共指研究中被广泛使用，但上游组件产生的错误可能会传播到共指组件并对其性能产生不利影响。为了解决这个问题，该补助金的第二个目标是探索一种方法，在这种方法中，管道中的多个任务以联合方式学习。虽然大多数关于语言处理联合学习的研究都集中在两个任务上，但这项工作旨在通过同时学习语义，话语和信息提取中的大量任务，将联合学习中所涉及的挑战提升到一个新的水平，这些任务都可以从学习过程中相互之间的交互和共指中受益。