The NYU System for the CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection

The NYU System for the CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection
复制标题

纽约大学 CoNLL-SIGMORPHON 2018 通用形态再变形共享任务系统

DOI:
--
复制
发表时间:
2018
期刊:
Conference on Computational Natural Language Learning
影响因子:
--
通讯作者:
Hinrich Schütze
Hinrich Schütze
中科院分区:
--
文献类型:
--
作者:
Katharina Kann;Hinrich Schütze

文献摘要

被引文献

相似文献

本文描述了纽约大学提交给CoNLL-SIGMORPHON 2018通用形态学再灌注共享任务的文件。我们的系统参与任务2轨道2的低资源设置,即,它在形态学上预测上下文中的省略形式:给定一个词元和一个上下文句子,它产生一个词元的形式,该词元的形式可能被用在句子中的一个指示位置。它基于标准的基于注意力的LSTM编码器-解码器模型,但使用多个编码器来处理上下文的所有部分以及引理。在正式的共享任务评估中,我们的系统在其参加的5个参赛作品中获得了第二好的结果,并大大超过了正式的基准。
This paper describes the NYU submission to the CoNLL–SIGMORPHON 2018 shared task on universal morphological reinflection. Our system participates in the low-resource setting of Task 2, track 2, i.e., it predicts morphologically inflected forms in context: given a lemma and a context sentence, it produces a form of the lemma which might be used at an indicated position in the sentence. It is based on the standard attention-based LSTM encoder-decoder model, but makes use of multiple encoders to process all parts of the context as well as the lemma. In the official shared task evaluation, our system obtains the second best results out of 5 submissions for the competition it entered and strongly outperforms the official baseline.