TU Darmstadt / ULB / TUbiblio

Character-Level Models versus Morphology in Semantic Role Labeling

Şahin, Gözde Gül and Steedman, Mark (2018):
Character-Level Models versus Morphology in Semantic Role Labeling.
In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), In: The 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 15.07.2018--20.07.2018, Long Papers, [Online-Edition: http://aclweb.org/anthology/P18-1036],
[Conference or Workshop Item]

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.

Item Type: Conference or Workshop Item
Erschienen: 2018
Creators: Şahin, Gözde Gül and Steedman, Mark
Title: Character-Level Models versus Morphology in Semantic Role Labeling
Language: English
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.

Title of Book: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018)
Volume: Long Papers
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Title: The 56th Annual Meeting of the Association for Computational Linguistics
Event Location: Melbourne, Australia
Event Dates: 15.07.2018--20.07.2018
Date Deposited: 31 Aug 2018 14:03
Official URL: http://aclweb.org/anthology/P18-1036
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item