Loading...
Loading...

Go to the content (press return)

Spectral learning of sequence taggers over continuous sequences

Author
Recasens, A.; Quattoni, A.J.
Type of activity
Presentation of work at congresses
Name of edition
ECML 2013 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Date of publication
2013
Presentation's date
2013-09
Book of congress proceedings
Machine Learning and Knowledge Discovery in Databases European Conference : ECML PKDD 2013, Proceedings, Part I
First page
289
Last page
304
Publisher
Springer-Verlag
DOI
https://doi.org/10.1007/978-3-642-40988-2_19 Open in new window
Repository
http://hdl.handle.net/2117/21208 Open in new window
URL
http://link.springer.com/chapter/10.1007/978-3-642-40988-2_19 Open in new window
Abstract
In this paper we present a spectral algorithm for learning weighted finite-state sequence taggers (WFSTs) over paired input-output sequences, where the input is continuous and the output discrete. WFSTs are an important tool for modelling paired input-output sequences and have numerous applications in real-world problems. Our approach is based on generalizing the class of weighted finite-state sequence taggers over discrete input-output sequences to a class where transitions are linear combinati...
Citation
Recasens, A.; Quattoni, A.J. Spectral learning of sequence taggers over continuous sequences. A: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. "Machine Learning and Knowledge Discovery in Databases European Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part I". Praga: Springer-Verlag, 2013, p. 289-304.
Group of research
LARCA - Laboratory of Relational Algorithmics, Complexity and Learnability

Participants

  • Recasens, Adria  (author and speaker )
  • Quattoni, Ariadna Julieta  (author and speaker )