Universal Dependencies and Morphology for Hungarian - and on the Price of Universality

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 356–365, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics Universal Dependencies and Morphology for Hungarian – and on the Price of Universality Veronika Vincze1,2, Katalin Ilona Simkó1, Zsolt Szántó1, Richárd Farkas1 1University of Szeged Institute of Informatics 2MTA-SZTE Research Group on Artificial Intelligence kata.simko@gmail.com {vinczev,szantozs,rfarkas}@inf.u-szeged.hu Abstract In this paper, we present how the princi- ples of universal dependencies and mor- phology have been adapted to Hungarian. We report the most challenging grammati- cal phenomena and our solutions to those. On the basis of the adapted guidelines, we have converted and manually corrected 1,800 sentences from the Szeged Tree- bank to universal dependency format. We also introduce experiments on this manu- ally annotated corpus for evaluating auto- matic conversion and the added value of language-specific, i.e. non-universal, an- notations. Our results reveal that convert- ing to universal dependencies is not nec- essarily trivial, moreover, using language- specific morphological features may have an impact on overall performance. 1 Introduction Morphological tagging and syntactic parsing are key components in most natural language process- ing (NLP) applications. Linguistic resources and parsers for morphological and syntactic analysis have been developed for several languages, see e.g. the shared tasks on morphologically rich lan- guages (Seddah et al., 2013; Seddah et al., 2014). However, the comparison of results achieved for different languages is not straightforward as most languages and databases apply a unique tagset, moreover, they were annotated following differ- ent guidelines. In order to overcome these issues, the project Universal Dependencies and Morphol- ogy (UD) has recently been initiated within the NLP community (Nivre, 2015). The main goal of the UD project is to develop a “universal”, i.e. a language-independent morphological and syntac- tic representation which can contribute to the im- plementation of multilingual morphological and syntactic parsers from a computational linguistic point of view. Furthermore, it can enhance studies on linguistic typology and contrastive linguistics. From the viewpoint of syntactic parsing, the languages of the world are usually categorized ac- cording to their level of morphological richness (which is negatively correlated with configura- tionality). At one end, there is English, a strongly configurational language while there is Hungarian at the other end of the spectrum with rich mor- phology and free word order (Fraser et al., 2013). In this paper, we present how UD principles were adapted to Hungarian, with special emphasis on Hungarian-specific phenomena. Hungarian is one of the prototypical morpho- logically rich languages thus our UD principles can provide important best practices for the uni- versalization of other morphologically rich lan- guages. The UD guidelines for Hungarian were motivated by both linguistic considerations and data-driven observations. We developed a con- verter from the existing Szeged Dependency Tree- bank (Vincze et al., 2010) to UD and manually corrected 1,800 sentences from the newspaper do- main. The experiences gained during the converter development and during the manual correction could reinforce the linguistic guidelines. …

Content truncated to 500 words