Hybrid Approaches to Neural Network-based Language Processing

TitleHybrid Approaches to Neural Network-based Language Processing
Publication TypeTechnical Report
Year of Publication1997
AuthorsWermter, S.
Other Numbers1095
Abstract

In this paper we outline hybrid approaches to artificial neural network-based natural language processing. We start by motivating hybrid symbolic/connectionist processing. Then we suggest various types of symbolic/connectionist integration for language processing: connectionist structure architectures, hybrid transfer architectures, hybrid processing architectures. Furthermore, we focus particularly on loosely coupled, tightly coupled, and fully integrated hybrid processing architectures. We give particular examples of these hybrid processing architectures and argue that the hybrid approach to artificial neural network-based language processing has a lot of potential to overcome the gap between a neural level and a symbolic conceptual level.

URLhttp://www.icsi.berkeley.edu/ftp/global/pub/techreports/1997/tr-97-030.pdf
Bibliographic Notes

ICSI Technical Report TR-97-030

Abbreviated Authors

S. Wermter

ICSI Publication Type

Technical Report