Generating Referring Expressions in Context: The GREC Task Evaluation Challenges

Generating Referring Expressions in Context: The GREC Task Evaluation Challenges
复制标题

在上下文中生成引用表达式:GREC 任务评估挑战

DOI:
10.1007/978-3-642-15573-4_15
复制
发表时间:
2010
期刊:
影响因子:
1.7
通讯作者:
Albert Gatt
Albert Gatt
中科院分区:
法学3区
文献类型:
--
作者:
A. Belz;Eric Kow;J. Viethen;Albert Gatt

文献摘要

被引文献

相似文献

直到最近,指称表达生成(reg)的研究主要集中在选择的任务,明确提到的语义内容,熟悉的话语实体。在grec的研究项目中,我们一直对一个版本的reg问题定义感兴趣,该定义(i)基于话语背景,(ii)嵌入应用背景,(iii)由自然发生的数据提供信息。本文概述了我们在这项研究计划中的目标和动机,我们已经建立的数据资源,以及前三个共享任务的挑战,GREC-MSR'08,GREC-MSR'09和GEEC-NEG'09,我们已经运行的数据的基础上。
Until recently, referring expression generation (reg) research focused on the task of selecting the semantic content of definite mentions of listener-familiar discourse entities. In the grec research programme we have been interested in a version of the reg problem definition that is (i) grounded within discourse context, (ii) embedded within an application context, and (iii) informed by naturally occurring data. This paper provides an overview of our aims and motivations in this research programme, the data resources we have built, and the first three sharedtask challenges, GREC-MSR'08, GREC-MSR'09 and GEEC-NEG'09, we have run based on the data.