Artificially Evolved Chunks for Morphosyntactic Analysis

Use this link to cite
http://hdl.handle.net/2183/36665Collections
- Investigación (FFIL) [842]
Metadata
Show full item recordTitle
Artificially Evolved Chunks for Morphosyntactic AnalysisDate
2019-08Citation
Mark 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.
Abstract
[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.
Keywords
Morphosyntactic Analysis
Evolutionary Algorithms
Dependency Parsing
Multi-task Learning
Evolutionary Algorithms
Dependency Parsing
Multi-task Learning
Description
It 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.
Editor version
Rights
Atribución 3.0 España