arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.08955cs.CL
收藏

英语增强普遍性并列结构的分析与计算建模

Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling

Institut für Maschinelle Sprachverarbeitung, University of Stuttgart(斯图加特大学机器语言研究所);Bosch Center for Artificial Intelligence(博世人工智能中心)

Stefan Grünewald, Prisca Piccirilli, Annemarie Friedrich

摘要:

在本文中,我们解决了增强的通用关联(UD),其中相关的依赖关系的链接从连接头传播到其他合取的坐标结构的表示。英语树银行增强UD已创建黄金基本依赖使用启发式规则为基础的转换器,它只传播核心参数。为了从语义的角度确定应该传播哪组链接,我们创建了一个大规模的手动编辑语法图数据集。我们确定在原始数据中的几个系统性错误,并建议也传播的pronts。我们观察到高注释者之间的协议,这个语义注释任务。使用我们新的手动验证数据集,我们对基于规则和(部分新颖的)基于机器学习的英语连词传播方法进行了第一次原则性比较。我们表明,学习传播规则比手工设计的启发式规则更有效。当使用自动解析器时,我们的基于神经图解析器的边缘预测器优于使用基本层树解析器加转换器的当前主流流水线。

英文摘要:

In this paper, we address the representation of coordinate constructions in Enhanced Universal Dependencies (UD), where relevant dependency links are propagated from conjunction heads to other conjuncts. English treebanks for enhanced UD have been created from gold basic dependencies using a heuristic rule-based converter, which propagates only core arguments. With the aim of determining which set of links should be propagated from a semantic perspective, we create a large-scale dataset of manually edited syntax graphs. We identify several systematic errors in the original data, and propose to also propagate adjuncts. We observe high inter-annotator agreement for this semantic annotation task. Using our new manually verified dataset, we perform the first principled comparison of rule-based and (partially novel) machine-learning based methods for conjunction propagation for English. We show that learning propagation rules is more effective than hand-designing heuristic rules. When using automatic parses, our neural graph-parser based edge predictor outperforms the currently predominant pipelinesusing a basic-layer tree parser plus converters.

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。

↑