NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED308709
Record Type: Non-Journal
Publication Date: 1986-Oct
Pages: 14
Abstractor: N/A
Reference Count: N/A
ISBN: N/A
ISSN: N/A
A Connectionist Network That Learns To Process Some (Very) Simple Sentences.
Samad, Tariq
The application of the "back-propagation" learning algorithm to the task of determining the right set of features corresponding to the words in an input sentence is described. Features that are specific to particular nouns and verbs, that indicate whether a nominal constituent is singular or plural, definite or indefinite, and that furnish case-frame information, are discussed. On examination, it appears that the network has learned concepts appropriate to the domain of natural language processing. The learning also generalizes well to novel sentences. Three related experiments are described. The shortcomings of the network are discussed, and ideas are suggested for an alternative model that should overcome some of these shortcomings. (Author/DJD)
Publication Type: Reports - Descriptive; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A