Learning Feature-Based Semantics with Simple Recurrent Networks

TitleLearning Feature-Based Semantics with Simple Recurrent Networks
Publication TypeTechnical Report
Year of Publication1990
AuthorsStolcke, A.
Other Numbers579
Abstract

The paper investigates the possibilities for using simple recurrent networks as transducers which map sequential natural language input into non-sequential feature-based semantics. The networks perform well on sentences containing a single main predicate (encoded by transitive verbs or prepositions) applied to multiple-feature objects (encoded as noun-phrases with adjectival modifiers), and shows robustness against ungrammatical inputs. A second set of experiments deals with sentences containing embedded structures. Here the network is able to process multiple levels of sentence-final embeddings but only one level of center-embedding. This turns out to be a consequence of the network's inability to retain information that is not reflected in the outputs over intermediate phases of processing. Two extensions to Elman's shortcite{Elman:88} original recurrent network architecture are introduced.

URLhttp://www.icsi.berkeley.edu/ftp/global/pub/techreports/1990/tr-90-015.pdf
Bibliographic Notes

ICSI Technical Report TR-90-015

Abbreviated Authors

A. Stolcke

ICSI Publication Type

Technical Report