Character-level models versus morphology in semantic role labeling
Şahin GG, Steedman M (2018)
Publication Type: Conference contribution
Publication year: 2018
Publisher: Association for Computational Linguistics (ACL)
Book Volume: 1
Pages Range: 386-396
Conference Proceedings Title: ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Event location: Melbourne, VIC, AUS
ISBN: 9781948087322
DOI: 10.18653/v1/p18-1036
Abstract
Character-level models have become a popular approach specially for their accessibility and ability to handle unseen data. However, little is known on their ability to reveal the underlying morphological structure of a word, which is a crucial skill for high-level semantic analysis tasks, such as semantic role labeling (SRL). In this work, we train various types of SRL models that use word, character and morphology level information and analyze how performance of characters compare to words and morphology for several languages. We conduct an in-depth error analysis for each morphological typology and analyze the strengths and limitations of character-level models that relate to out-of-domain data, training data size, long range dependencies and model complexity. Our exhaustive analyses shed light on important characteristics of character-level models and their semantic capability.
Involved external institutions
Germany (DE)
United Kingdom (GB)How to cite
APA:
Şahin, G.G., & Steedman, M. (2018). Character-level models versus morphology in semantic role labeling. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (pp. 386-396). Melbourne, VIC, AUS: Association for Computational Linguistics (ACL).
MLA:
Şahin, Gözde Gül, and Mark Steedman. "Character-level models versus morphology in semantic role labeling." Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, VIC, AUS Association for Computational Linguistics (ACL), 2018. 386-396.
BibTeX: Download