Compositional Matrix-Space Models of Language

Sebastian RudolphSebastian Rudolph, Eugenie GiesbrechtEugenie Giesbrecht

Download

Sebastian Rudolph, Eugenie Giesbrecht
Compositional Matrix-Space Models of Language
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, 907-916, July 2010. Association for Computational Linguistics

Details
Bibtex

KurzfassungAbstract
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.
Bemerkung: Note: to appear
Projekt:Project: Multipla
Forschungsgruppe:Research Group: Wissensmanagement„Wissensmanagement“ befindet sich nicht in der Liste (Computational Logic, Automatentheorie, Wissensverarbeitung, Knowledge-Based Systems, Knowledge Systems, Wissensbasierte Systeme, Logische Programmierung und Argumentation, Algebra und Diskrete Strukturen, Knowledge-aware Artificial Intelligence, Algebraische und logische Grundlagen der Informatik) zulässiger Werte für das Attribut „Forschungsgruppe“.Wissensmanagement

@inproceedings{RG2010,
  author    = {Sebastian Rudolph and Eugenie Giesbrecht},
  title     = {Compositional Matrix-Space Models of Language},
  booktitle = {Proceedings of the 48th Annual Meeting of the Association for
               Computational Linguistics},
  publisher = {Association for Computational Linguistics},
  year      = {2010},
  month     = {July},
  pages     = {907-916}
}