Stage-oe-small.jpg

Inproceedings3055: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Rudolph |ErsterAutorVorname=Sebastian }} {{Publikation Author |Rank=2 |Author=Eugenie Giesbrecht }} {{Inproceeding…“)
 
Zeile 18: Zeile 18:
 
{{Publikation Details
 
{{Publikation Details
 
|Abstract=We propose CMSMs, a novel type of generic compositional models for syntactic and semantic aspects of natural language, based on matrix multiplication. We argue for the structural and cognitive plausibility of this model and show that it is able to cover and combine various common compositional NLP approaches ranging from statistical word space models to symbolic grammar formalisms.
 
|Abstract=We propose CMSMs, a novel type of generic compositional models for syntactic and semantic aspects of natural language, based on matrix multiplication. We argue for the structural and cognitive plausibility of this model and show that it is able to cover and combine various common compositional NLP approaches ranging from statistical word space models to symbolic grammar formalisms.
 +
|Download=RuGi-ACL2010.pdf,
 
|Projekt=Multipla
 
|Projekt=Multipla
 
|Forschungsgruppe=Wissensmanagement
 
|Forschungsgruppe=Wissensmanagement

Version vom 13. Mai 2010, 23:07 Uhr


Compositional Matrix-Space Models of Language


Compositional Matrix-Space Models of Language



Published: 2010 Juli

Buchtitel: Proceedings of ACL 2010
Verlag: ACL

Referierte Veröffentlichung
Note: to appear

BibTeX

Kurzfassung
We propose CMSMs, a novel type of generic compositional models for syntactic and semantic aspects of natural language, based on matrix multiplication. We argue for the structural and cognitive plausibility of this model and show that it is able to cover and combine various common compositional NLP approaches ranging from statistical word space models to symbolic grammar formalisms.

Download: Media:RuGi-ACL2010.pdf

Projekt

Multipla



Forschungsgruppe

Wissensmanagement


Forschungsgebiet

Information Retrieval, Natürliche Sprachverarbeitung