arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.01446cs.CL
收藏

自由词序中的自由:一个基于能量的梵语分词和词法标注模型

Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit

IIT Kharagpur(印度理工学院克勒格布尔分校);Flipkart(Flipkart公司);University of Waterloo(滑铁卢大学);American Express India Pvt Ltd(美国运通印度私人有限公司);Chinmaya Vishwavidyapeeth(钦玛雅大学)

Amrith Krishna, Bishal Santra, Sasi Prasanth Bandaru, Gaurav Sahu, Vishnu Dutt Sharma, Pavankumar Satuluri, Pawan Goyal

摘要:

在自由词序语言(如梵语)的句子中,构形信息的使用是有限的。因此,即使对于诸如分词之类的基本处理任务,整个句子的上下文也将是期望的。我们提出了一个结构化的预测框架,共同解决了分词和形态标记的梵文任务。我们建立了一个基于能量的模型,其中我们采用了基于图的解析技术中通常采用的方法(McDonald等人,2005 a; Carreras,2007)。我们的模型以96.92的F分数(7.06%的百分比提高)优于最先进的技术,同时使用不到十分之一的特定于任务的训练数据。我们发现,使用基于图的方法,而不是传统的基于网格的顺序标记方法,导致分割任务的F分数的百分比增益为12.6%。

英文摘要:

The configurational information in sentences of a free word order language such as Sanskrit is of limited use. Thus, the context of the entire sentence will be desirable even for basic processing tasks such as word segmentation. We propose a structured prediction framework that jointly solves the word segmentation and morphological tagging tasks in Sanskrit. We build an energy based model where we adopt approaches generally employed in graph based parsing techniques (McDonald et al., 2005a; Carreras, 2007). Our model outperforms the state of the art with an F-Score of 96.92 (percentage improvement of 7.06%) while using less than one-tenth of the task-specific training data. We find that the use of a graph based ap- proach instead of a traditional lattice-based sequential labelling approach leads to a percentage gain of 12.6% in F-Score for the segmentation task.

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。

↑