A Neural Morphological Analyzer for Arapaho Verbs Learned from a Finite State Transducer
A Neural Morphological Analyzer for Arapaho Verbs Learned from a Finite State Transducer
复制标题
从有限状态换能器学习的 Arapaho 动词的神经形态分析器
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Mans Hulden
中科院分区：
文献类型：
--
作者：
Sarah R. Moeller;Ghazaleh Kazeminejad;Andrew Cowell;Mans Hulden
我们通过训练一个编码器-解码器神经模型来模拟现有的Arapaho动词的手写有限状态形态语法行为，Arapaho动词是一种具有高度复杂词形变化系统的多合成语言。在对歧义解析进行调整后，我们发现系统能够推广到未见过的形式，准确率为98.68%（无歧义动词）和92.90%（所有动词）。
We experiment with training an encoder-decoder neural model for mimicking the behavior of an existing hand-written finite-state morphological grammar for Arapaho verbs, a polysynthetic language with a highly complex verbal inflection system. After adjusting for ambiguous parses, we find that the system is able to generalize to unseen forms with accuracies of 98.68% (unambiguous verbs) and 92.90% (all verbs).