arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08512cs.CL
收藏

形态拐点的最小监督

Minimal Supervision for Morphological Inflection

Bar Ilan University(巴伊兰大学)

Omer Goldman, Reut Tsarfaty

摘要:

神经模型的各种口味的形态变化的任务已被证明是非常准确的充分标记的数据-数据可能是缓慢和昂贵的获得。在这项工作中,我们的目标是克服这个注释瓶颈,引导标记的数据从一个种子少到{ \em five}标记的范例,伴随着大量的未标记的文本。我们的方法在两个阶段的设置中利用形态系统中的不同种类的匹配,其中基于{ \em类比}的词标记之后是基于{ \em距离}的词配对。我们的实验与范式细胞填充问题超过8个类型学上不同的语言,并发现,在语言相对简单的形态,正字法的字母对自己允许变形模型,以实现可观的准确性。组合的拼写和语义的语法减轻了特别复杂的形态-语音系统的困难。我们的研究结果表明,手工制作许多标记的例子可能是不必要的努力。然而,还需要做更多的工作,以处理很少使用的表格。

英文摘要:

Neural models for the various flavours of morphological inflection tasks have proven to be extremely accurate given ample labeled data -- data that may be slow and costly to obtain. In this work we aim to overcome this annotation bottleneck by bootstrapping labeled data from a seed as little as {\em five} labeled paradigms, accompanied by a large bulk of unlabeled text. Our approach exploits different kinds of regularities in morphological systems in a two-phased setup, where word tagging based on {\em analogies} is followed by word pairing based on {\em distances}. We experiment with the Paradigm Cell Filling Problem over eight typologically different languages, and find that, in languages with relatively simple morphology, orthographic regularities on their own allow inflection models to achieve respectable accuracy. Combined orthographic and semantic regularities alleviate difficulties with particularly complex morpho-phonological systems. Our results suggest that hand-crafting many tagged examples might be an unnecessary effort. However, more work is needed in order to address rarely used forms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑