Inproceedings3055: Unterschied zwischen den Versionen
Aus Aifbportal
Sru (Diskussion | Beiträge) |
Sru (Diskussion | Beiträge) |
||
Zeile 12: | Zeile 12: | ||
|Year=2010 | |Year=2010 | ||
|Month=Juli | |Month=Juli | ||
− | |Booktitle=Proceedings of | + | |Booktitle=Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics |
− | |Publisher= | + | |Pages=907-916 |
+ | |Publisher=Association for Computational Linguistics | ||
|Note=to appear | |Note=to appear | ||
}} | }} | ||
{{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, | + | |Download=RuGi-ACL2010.pdf, |
|Projekt=Multipla | |Projekt=Multipla | ||
|Forschungsgruppe=Wissensmanagement | |Forschungsgruppe=Wissensmanagement |
Aktuelle Version vom 14. August 2010, 14:08 Uhr
Compositional Matrix-Space Models of Language
Compositional Matrix-Space Models of Language
Published: 2010
Juli
Buchtitel: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Seiten: 907-916
Verlag: Association for Computational Linguistics
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
Forschungsgruppe
Forschungsgebiet
Information Retrieval, Natürliche Sprachverarbeitung