Skip to Main content Skip to Navigation

Discontinuous Constituency Parsing of Morphologically Rich Languages

Abstract : Syntactic parsing consists in assigning syntactic trees to sentences in natural language. Syntactic parsing of non-configurational languages, or languages with a rich inflectional morphology, raises specific problems. These languages suffer more from lexical data sparsity and exhibit word order variation phenomena more frequently. For these languages, exploiting information about the internal structure of word forms is crucial for accurate parsing. This dissertation investigates transition-based methods for robust discontinuous constituency parsing. First of all, we propose a multitask learning neural architecture that performs joint parsing and morphological analysis. Then, we introduce a new transition system that is able to predict discontinuous constituency trees, i.e.\ syntactic structures that can be seen as derivations of mildly context-sensitive grammars, such as LCFRS. Finally, we investigate the question of lexicalization in syntactic parsing. Some syntactic parsers are based on the hypothesis that constituents are organized around a lexical head and that modelling bilexical dependencies is essential to solve ambiguities. We introduce an unlexicalized transition system for discontinuous constituency parsing and a scoring model based on constituent boundaries. The resulting parser is simpler than lexicalized parser and achieves better results in both discontinuous and projective constituency parsing.
Complete list of metadata

Cited literature [202 references]  Display  Hide  Download
Contributor : Maximin Coavoux Connect in order to contact the contributor
Submitted on : Tuesday, October 1, 2019 - 4:30:07 PM
Last modification on : Friday, June 12, 2020 - 9:36:03 AM


Files produced by the author(s)


  • HAL Id : tel-02302563, version 1


Maximin Coavoux. Discontinuous Constituency Parsing of Morphologically Rich Languages. Computation and Language [cs.CL]. Université Sorbonne Paris Cité, 2017. English. ⟨tel-02302563⟩



Record views


Files downloads