Incremental nonmonotonic parsing through semantic self-organization
Lists
Only you see this
Abstract
Subsymbolic systems have been successfully used to model several aspects of human language processing. Subsymbolic parsers are appealing because they allow combining syntactic, semantic, and thematic constraints in sentence interpretation and revising that interpretation as each word is read in. These parsers are also cognitively plausible: processing is robust and multiple interpretations are simultaneously activated when the input is ambiguous. Yet, it has been very difficult to scale them up to realistic language. They have limited memory capacity, training takes a long time, and it is difficult to represent linguis-tic structure. In this study, we propose to scale up the subsym-bolic approach by utilizing semantic self-organization. The resulting architecture, INSOMNET, was trained on seman-tic representations of the newly-released LINGO Redwoods HPSG Treebank of annotated sentences from the VerbMobil project. The results show that INSOMNET is able to accu-rately represent the semantic dependencies while demonstrat-ing expectations and defaults, coactivation of multiple inter-pretations, and robust parsing of noisy input.
BibTeX
@inproceedings{mayberry2003incremental,
author = {Marshall R. Mayberry and Risto Miikkulainen},
title = {{Incremental nonmonotonic parsing through semantic self-organization}},
booktitle = {eScholarship},
year = {2003},
}Loading related content...