Abstract
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 POS1 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.