Aliannejadi, Mohammad ; Kiaeeha, Masoud ; Khadivi, Shahram ; Ghidary, Saeed Shiry (2014)
Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data.
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
We experiment graph-based SemiSupervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data. The aligned labels for examples are obtained using IBM Model. We adapt a baseline semisupervised CRF by defining new feature set and altering the label propagation algorithm. Our results demonstrate that our proposed approach significantly improves the performance of the supervised model by utilizing the knowledge gained from the graph.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2014 |
| Autor(en): | Aliannejadi, Mohammad ; Kiaeeha, Masoud ; Khadivi, Shahram ; Ghidary, Saeed Shiry |
| Art des Eintrags: | Bibliographie |
| Titel: | Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data |
| Sprache: | Deutsch |
| Publikationsjahr: | November 2014 |
| Buchtitel: | Australasian Language Technology Association Workshop |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | We experiment graph-based SemiSupervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data. The aligned labels for examples are obtained using IBM Model. We adapt a baseline semisupervised CRF by defining new feature set and altering the label propagation algorithm. Our results demonstrate that our proposed approach significantly improves the performance of the supervised model by utilizing the knowledge gained from the graph. |
| ID-Nummer: | TUD-CS-2014-1045 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 31 Dez 2016 14:29 |
| Letzte Änderung: | 06 Feb 2020 13:45 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum