Anderson, MarkVilares, DavidGómez-Rodríguez, Carlos2024-05-282024-05-282019-08Mark Anderson, David Vilares, and Carlos Gómez-Rodríguez. 2019. Artificially Evolved Chunks for Morphosyntactic Analysis. In Proceedings of the 18th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2019), pages 133–143, Paris, France. Association for Computational Linguistics.http://hdl.handle.net/2183/36665It was held on the last week of August (Aug 26-30), in the center of Paris, in the "Grand amphitheatre du Monde anglophone" of the Sorbonne Nouvelle.[Absctract]: We introduce a language-agnostic evolutionary technique for automatically extracting chunks from dependency treebanks. We evaluate these chunks on a number of morphosyntactic tasks, namely POS tagging, morphological feature tagging, and dependency parsing. We test the utility of these chunks in a host of different ways. We first learn chunking as one task in a shared multitask framework together with POS and morphological feature tagging. The predictions from this network are then used as input to augment sequence-labelling dependency parsing. Finally, we investigate the impact chunks have on dependency parsing in a multi-task framework. Our results from these analyses show that these chunks improve performance at different levels of syntactic abstraction on English UD treebanks and a small, diverse subset of non-English UD treebanks.engAtribución 3.0 Españahttp://creativecommons.org/licenses/by/3.0/es/Morphosyntactic analysisEvolutionary algorithmsDependency parsingMulti-task learningconference outputopen access