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)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (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.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2018 |
| Autor(en): | Şahin, Gözde Gül ; Steedman, Mark |
| Art des Eintrags: | Bibliographie |
| Titel: | Character-Level Models versus Morphology in Semantic Role Labeling |
| Sprache: | Englisch |
| Publikationsjahr: | 15 Juli 2018 |
| Buchtitel: | Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) |
| Band einer Reihe: | Long Papers |
| Veranstaltungstitel: | The 56th Annual Meeting of the Association for Computational Linguistics |
| Veranstaltungsort: | Melbourne, Australia |
| Veranstaltungsdatum: | 15.07.2018--20.07.2018 |
| URL / URN: | http://aclweb.org/anthology/P18-1036 |
| Zugehörige Links: | |
| Kurzbeschreibung (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. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 31 Aug 2018 14:03 |
| Letzte Änderung: | 16 Nov 2018 14:57 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum