![]() | ![]() |
![]() | |
Verfasst von: | Do, Bich-Ngoc [VerfasserIn] ![]() |
Rehbein, Ines [VerfasserIn] ![]() | |
Titel: | Neural PP attachment disambiguation systems |
Verf.angabe: | Bich-Ngoc Do, Ines Rehbein |
Verlagsort: | Heidelberg |
Verlag: | Universität |
E-Jahr: | 2023 |
Jahr: | 2023-11-13 |
Umfang: | 1 Online-Ressource (16 Files) |
Fussnoten: | Produktionsdatum: 2020 ; Gesehen am 22.11.2023 |
Abstract: | This resource contains code for different types of neural PP attachment disambiguation systems: A disambiguation system inspired by de Kok et al. (2017) but with the ranking loss function. A disambiguation system with biaffine attention similar to the neural dependency parser in Dozat and Manning (2017). The systems are described in details in the paper: Do and Rehbein (2020). "Parsers Know Best: German PP Attachment Revisited". We also include all pre-trained models reported in the paper. |
DOI: | doi:10.11588/data/DKWKGJ |
URL: | kostenfrei: Volltext: https://doi.org/10.11588/data/DKWKGJ |
kostenfrei: Volltext: https://heidata.uni-heidelberg.de/dataset.xhtml?persistentId=doi:10.11588/data/DKWKGJ | |
kostenfrei: Volltext: https://github.com/bichngocdo/biaffine-pp-disambiguation | |
DOI: https://doi.org/10.11588/data/DKWKGJ | |
Datenträger: | Online-Ressource |
Dokumenttyp: | Forschungsdaten |
Datenbank | |
Sprache: | eng |
Bibliogr. Hinweis: | Forschungsdaten zu: Do, Bich-Ngoc, 1989 - : Parsers know best |
Sach-SW: | Arts and Humanities |
Computer and Information Science | |
K10plus-PPN: | 1871577489 |
Lokale URL UB: | ![]() |