MED: The LMU System for the SIGMORPHON 2016 Shared Task on Morphological Reinflection
MED: The LMU System for the SIGMORPHON 2016 Shared Task on Morphological Reinflection
复制标题
MED：SIGMORPHON 2016 形态再变形共享任务的 LMU 系统
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Hinrich Schütze
中科院分区：
文献类型：
--
作者：
Katharina Kann;Hinrich Schütze
本文介绍了MED，LMU团队的主要系统，用于SIGMORPHON 2016共享任务的形态反射，以及对不同设计选择如何影响最终性能的扩展分析。我们使用神经编码器-解码器模型以及将输入编码为源和目标形式的形态标签的单个序列以及源形式的字母序列来建模形态反射的任务。共享任务包括三个子任务，三个不同的轨道，涵盖10种不同的语言，以鼓励使用语言独立的方法。MED是具有整体最佳性能的系统，证明我们的方法适用于SIGMORPHON 2016共享任务的低资源设置。
This paper presents MED, the main system of the LMU team for the SIGMORPHON 2016 Shared Task on Morphological Reinflection as well as an extended analysis of how different design choices contribute to the final performance. We model the task of morphological reinflection using neural encoder-decoder models together with an encoding of the input as a single sequence of the morphological tags of the source and target form as well as the sequence of letters of the source form. The Shared Task consists of three subtasks, three different tracks and covers 10 different languages to encourage the use of language-independent approaches. MED was the system with the overall best performance, demonstrating our method generalizes well for the low-resource setting of the SIGMORPHON 2016 Shared Task.