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 Wolfgang Seeker and ¨Ozlem C¸ etino˘glu Institut f¨ur Maschinelle Sprachverarbeitung University of Stuttgart {seeker,ozlem}@ims.uni-stuttgart.de Abstract Space-delimited words in Turkish and He- brew text can be further segmented into mean- ingful units, but syntactic and semantic con- text is necessary to predict segmentation. At the same time, predicting correct syntac- tic structures relies on correct segmentation. We present a graph-based lattice dependency parser that operates on morphological lattices to represent different segmentations and mor- phological 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 outper- forms three state-of-the-art pipeline systems on both data sets. Our work corroborates find- ings from constituency lattice parsing for He- brew and presents the first results for full lat- tice parsing on Turkish. 1 Introduction Linguistic theory has provided examples from many different languages in which grammatical informa- tion is expressed via case marking, morphological agreement, or clitics. In these languages, configura- tional information is less important than in English since the words are overtly marked for their syntac- tic relations to each other. Such morphologically rich languages pose many new challenges to today’s natural language processing technology, which has often been developed for English. One of the first challenges is the question on how to represent morphologically rich languages and what are the basic units of analysis (Tsarfaty et al., 2010). The Turkish treebank (Oflazer et al., 2003), for example, represents words as sequences of inflectional groups, semantically coherent groups of morphemes separated by derivational boundaries. The treebank for Modern Hebrew (Sima’an et al., 2001) chooses morphemes as the basic unit of rep- resentation. A space-delimited word in the treebank can consist of several morphemes that may belong to independent syntactic contexts. Both Turkish and Hebrew show high amounts of ambiguity when it comes to the correct segmentation of words into inflectional groups and morphemes, respectively. Within a sentence, however, these am- biguities can often be resolved by the syntactic and semantic context in which these words appear. A standard (dependency) parsing system de- cides segmentation, morphological analysis (includ- ing POS), and syntax one after the other in a pipeline setup. While pipelines are fast and efficient, they cannot model interaction between these different levels of analysis, however. It has therefore been argued that joint modeling of these three tasks is more suitable to the problem (Tsarfaty, 2006). In previous research, several transition-based parsers have been proposed to model POS/morphological tagging and parsing jointly (Hatori et al., 2011; Bohnet and Nivre, 2012; Bohnet et al., 2013). Such parsing systems have been further extended to also solve the segmentation problem in Chinese (Ha- tori et al., 2012; Li and Zhou, 2012; Zhang et al., 2014). Transition-based parsers are attractive since 359 Transactions of the Association …

Content truncated to 500 words