Parsers know best: German PP attachment revisited
In the paper, we revisit the PP attachment problem which has been identified as one of the major sources for parser errors and discuss shortcomings of recent work. In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the sy...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Kapitel/Artikel Konferenzschrift |
| Sprache: | Englisch |
| Veröffentlicht: |
2020
|
| In: |
The 28th International Conference on Computational Linguistics - proceedings of the conference
Year: 2020, Pages: 2049-2061 |
| DOI: | 10.18653/v1/2020.coling-main.185 |
| Online-Zugang: | Resolving-System, kostenfrei, Volltext: https://doi.org/10.18653/v1/2020.coling-main.185 Verlag, kostenfrei, Volltext: https://aclanthology.org/2020.coling-main.185 
|
| Verfasserangaben: | Bich-Ngoc Do, Ines Rehbein |
| Zusammenfassung: | In the paper, we revisit the PP attachment problem which has been identified as one of the major sources for parser errors and discuss shortcomings of recent work. In particular, we show that using gold information for the extraction of attachment candidates as well as a missing comparison of the system's output to the output of a full syntactic parser leads to an overly optimistic assessment of the results. We address these issues by presenting a realistic evaluation of the potential of different PP attachment systems, using fully predicted information as system input. We compare our results against the output of a strong neural parser and show that the full parsing approach is superior to modeling PP attachment disambiguation as a separate task. |
|---|---|
| Beschreibung: | Gesehen am 29.11.2023 |
| Beschreibung: | Online Resource |
| ISBN: | 9781952148279 |
| DOI: | 10.18653/v1/2020.coling-main.185 |