Artificially Evolved Chunks for Morphosyntactic Analysis
Mark D. Anderson, David Vilares, Carlos Gómez‐Rodríguez · 2019
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 1 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.