Joint Transition-Based Models for Morpho-Syntactic Parsing: Parsing Strategies for MRLs and a Case Study from Modern Hebrew

Joint Transition-Based Models for Morpho-Syntactic Parsing: Parsing Strategies for MRLs and a Case Study from Modern Hebrew Amir More Open University Ra’anana, Israel habeanf@gmail.com Amit Seker Open University Ra’anana, Israel amitse@openu.ac.il Victoria Basmova Open University Ra’anana, Israel vicbas@openu.ac.il Reut Tsarfaty Open University Ra’anana, Israel reutts@openu.ac.il Abstract In standard NLP pipelines, morphological analysis and disambiguation (MA&D) pre- cedes syntactic and semantic downstream tasks. However, for languages with complex and ambiguous word-internal structure, known as morphologically rich languages (MRLs), it has been hypothesized that syntactic context may be crucial for accurate MA&D, and vice versa. In this work we empirically confirm this hypothesis for Modern Hebrew, an MRL with complex morphology and severe word- level ambiguity, in a novel transition-based framework. Specifically, we propose a joint morphosyntactic transition-based framework which formally unifies two distinct transition systems, morphological and syntactic, into a single transition-based system with joint train- ing and joint inference. We empirically show that MA&D results obtained in the joint settings outperform MA&D results obtained by the respective standalone components, and that end-to-end parsing results obtained by our joint system present a new state of the art for Hebrew dependency parsing. 1 Introduction NLP research in recent years has shown in- creasing interest in parsing typologically differ- ent languages, as evident, for instance, by the universal dependencies1 initiative (Nivre et al., 2016). In particular, much attention is drawn to parsing morphologically rich languages (MRLs), which differ significantly from English in their structure and characteristics (Tsarfaty et al., 2010). In MRLs, grammatical information, typically expressed using word order in English, is often manifested in the internally complex structure of the words. Words in MRLs may carry, in addition to lexical content, functional affixes and clitics that correspond to additional pieces of information. In Modern Hebrew, for example, the inflected verb ‘‘ahbtih’’2 (loved + 1pers.singular.past + 3pers.feminine.singular) corresponds to three different grammatical functions: the subject ‘‘I,’’ the predicate ‘‘loved,’’ and the direct object ‘‘her.’’ Similarly, Spanish d´amelo corresponds to a predicate, an indirect object, and a direct object, as in ‘‘give it to me.’’ Thus, in MRLs, morphological analysis (MA) which translates raw space-delimited tokens to syntactically relevant ‘‘word’’ units is a necessary condition for any syntactic or semantic downstream task. However, raw space-delimited tokens in MRLs are often highly ambiguous. In Hebrew, Arabic, and other Semitic languages, this situation is further complicated by fact that written texts lack diacritics. The Hebrew token ‘‘fmn,’’ for instance, may be read as the noun ‘‘oil,’’ the adjective ‘‘fat,’’ the verb ‘‘lubricated,’’ the sequence 1http://universaldependencies.org/. 2Using the transliteration of Sima’an et al. (2001). 33 Transactions of the Association for Computational Linguistics, vol. 7, pp. 33–48, 2019. Action Editor: Masaaki Nagata. Submission batch: 5/2018; Revision batch: 8/2018; Published 3/2019. c⃝ 2019 Association for Computational Linguistics. Distributed under a CC-BY 4.0 license. Figure 1: The morphological and syntactic interactions in the analysis of the Hebrew phrase ‘‘bclm hneim’’ according to the Hebrew SPMRL annotation. ‘‘that’’+‘‘of,’’ or the phrase ‘‘their’’+‘‘name,’’ only one of which is relevant in context. This …

Content truncated to 500 words