Relational Learning for NLP using Linear Threshold Elements

Full Text

Authors:

R. Khardon and Dan Roth and L. G. Valiant

Abstract:

We describe a coherent view of learning and reasoning with relational representations in the context of natural language processing. In particular, we discuss the Neuroidal Architecture, Inductive Logic Programming and the SNoW system explaining the relationships among these, and thereby offer an explanation of the theoretical basis for the SNoW system. We suggest that extensions of this system along the lines suggested by the theory may provide new levels of scalability and functionality.

Citation:

R. Khardon and D. Roth and L. G. Valiant, Relational Learning for NLP using Linear Threshold Elements. IJCAI  (1999) pp. 911--917

Bibitem:

@conference{KhardonRoVa99,
  author = {R. Khardon and D. Roth and L. G. Valiant},
  title = {Relational Learning for NLP using Linear Threshold Elements},
  booktitle = {IJCAI},
  pages = {911--917},
  year = {1999},
  acceptance = {195/750 (26\%)},
  url = " http://cogcomp.cs.illinois.edu/papers/ijcai99krv.pdf",
  funding = {NSF98 KDI},
  projects = {KR,LT,NLP},
}