TU Darmstadt / ULB / TUbiblio

Character-Level Models versus Morphology in Semantic Role Labeling

Şahin, Gözde Gül ; Steedman, Mark (2018)
Character-Level Models versus Morphology in Semantic Role Labeling.
The 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia (15.07.2018--20.07.2018)
Conference or Workshop Item, Bibliographie

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 ; Steedman, Mark
Type of entry: Bibliographie
Title: Character-Level Models versus Morphology in Semantic Role Labeling
Language: English
Date: 15 July 2018
Book Title: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018)
Series Volume: Long Papers
Event Title: The 56th Annual Meeting of the Association for Computational Linguistics
Event Location: Melbourne, Australia
Event Dates: 15.07.2018--20.07.2018
URL / URN: http://aclweb.org/anthology/P18-1036
Corresponding Links:
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.

Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Date Deposited: 31 Aug 2018 14:03
Last Modified: 16 Nov 2018 14:57
PPN:
Corresponding Links:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details