A Graph-based Lattice Dependency Parser for Joint Morphological Segmentation and Syntactic Analysis
A Graph-based Lattice Dependency Parser for Joint Morphological Segmentation and Syntactic Analysis
复制标题
DOI：
10.1162/tacl_a_00144
复制
发表时间：
2015-06
影响因子：
10.9
通讯作者：
Wolfgang Seeker;Özlem Çetinoğlu
中科院分区：
文献类型：
--
作者：
Wolfgang Seeker;Özlem Çetinoğlu
土耳其语和希伯来语文本中以空格分隔的单词可以进一步切分成有意义的单元，但需要句法和语义上下文来预测切分。同时，预测正确的句法结构依赖于正确的切分。我们提出了一个基于图的格依存关系解析器，它在形态格上操作，以表示对给定输入句子的不同切分和形态分析。格子解析器预测格子中路径上的依存关系树，从而解决分割、形态分析和句法分析的联合任务。我们在土耳其语和希伯来语树库上进行了实验，结果表明，联合模型在这两个数据集上的性能都优于三个最先进的管道系统。我们的工作证实了希伯来语选区格分析的结果，并首次给出了土耳其语全格分析的结果。
Space-delimited words in Turkish and Hebrew text can be further segmented into meaningful units, but syntactic and semantic context is necessary to predict segmentation. At the same time, predicting correct syntactic structures relies on correct segmentation. We present a graph-based lattice dependency parser that operates on morphological lattices to represent different segmentations and morphological analyses for a given input sentence. The lattice parser predicts a dependency tree over a path in the lattice and thus solves the joint task of segmentation, morphological analysis, and syntactic parsing. We conduct experiments on the Turkish and the Hebrew treebank and show that the joint model outperforms three state-of-the-art pipeline systems on both data sets. Our work corroborates findings from constituency lattice parsing for Hebrew and presents the first results for full lattice parsing on Turkish.