Shared Task Proposal: Multilingual Surface Realization Using Universal Dependency Trees
Shared Task Proposal: Multilingual Surface Realization Using Universal Dependency Trees
复制标题
DOI：
10.18653/v1/w17-3517
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
Simon Mille;Bernd Bohnet;Leo Wanner;A. Belz
中科院分区：
文献类型：
--
作者：
Simon Mille;Bernd Bohnet;Leo Wanner;A. Belz
我们提出了一个多语言表面实现的共同任务，即，将无序和未变形的通用依赖树映射到许多语言中正确有序和变形的句子。第二个更深层次的输入将是可用的，此外，功能词，细粒度的PoS和形态信息将从输入树中删除。Surface Realization的第一个共享任务是在2011年进行的，采用了类似的设置，重点是英语。我们认为，现在是时候重新启动这样一个共享的任务工作了，一方面是因为大量语言的通用注释树库的到来，另一方面是因为深度学习的主导地位日益增强，它被证明是NLP的游戏规则改变者。
We propose a shared task on multilingual Surface Realization, i.e., on mapping unordered and uninflected universal dependency trees to correctly ordered and inflected sentences in a number of languages. A second deeper input will be available in which, in addition, functional words, fine-grained PoS and morphological information will be removed from the input trees. The first shared task on Surface Realization was carried out in 2011 with a similar setup, with a focus on English. We think that it is time for relaunching such a shared task effort in view of the arrival of Universal Dependencies annotated treebanks for a large number of languages on the one hand, and the increasing dominance of Deep Learning, which proved to be a game changer for NLP, on the other hand.