---
title: "Relational Learning for NLP using Linear Threshold Elements"
authors:
  - "Roni Khardon"
  - "Dan Roth"
  - "Leslie G. Valiant"
doi: ""
url: "https://ijcai.org/proceedings/1999/130"
pdf: "https://ijcai.org/proceedings/1999/0130.pdf"
venue: "Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence"
year: 1999
pages: "911-918"
track: "Natural Language Processing"
keywords:
---

# Relational Learning for NLP using Linear Threshold Elements

Roni Khardon, Dan Roth, Leslie G. Valiant

*Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence*, pages 911-918.

## Abstract

We describe a coherent view of learning and reasoning with relational representations in the context of natural language processing. In particular, we discuss th e 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.