Kuhn, Jonas ; Eckle-Kohler, Judith ; Rohrer, Christian (1998)
Lexicon Acquisition with and for Symbolic NLP-Systems – a Bootstrapping Approach.
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
We present a method of applying a broad-coverage LFG grammar of German in the process of semi-automatic lexicon acquisition from corpora. The identification of corpus instances that illustrate a certain subcategorization frame uniquely is done by a comparison of the numbers of analyses the grammar assigns to the corpus instances, under the assumption of different hypothetical lexicon entries for the candidate verb. Filtering conditions expressed on the feature representation output by the grammar further restrict the sentences that the automatic extraction step is based on. Experiments show that the grammar-based method produces better results than a method based on patterns in a corpus query language.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 1998 |
| Autor(en): | Kuhn, Jonas ; Eckle-Kohler, Judith ; Rohrer, Christian |
| Art des Eintrags: | Bibliographie |
| Titel: | Lexicon Acquisition with and for Symbolic NLP-Systems – a Bootstrapping Approach. |
| Sprache: | Englisch |
| Publikationsjahr: | 1998 |
| Buchtitel: | Proceedings of the First International Conference on Language Resources and Evaluation (LREC98) |
| URL / URN: | https://eckle-kohler.de/kuhn_ecklekohler_rohrer_98.pdf |
| Kurzbeschreibung (Abstract): | We present a method of applying a broad-coverage LFG grammar of German in the process of semi-automatic lexicon acquisition from corpora. The identification of corpus instances that illustrate a certain subcategorization frame uniquely is done by a comparison of the numbers of analyses the grammar assigns to the corpus instances, under the assumption of different hypothetical lexicon entries for the candidate verb. Filtering conditions expressed on the feature representation output by the grammar further restrict the sentences that the automatic extraction step is based on. Experiments show that the grammar-based method produces better results than a method based on patterns in a corpus query language. |
| ID-Nummer: | TUD-CS-1998-0003 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 31 Dez 2016 14:29 |
| Letzte Änderung: | 10 Sep 2018 18:58 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum