Modelling the interpretation of novel compounds

Lynott, Dermot and Keane, Mark T. (2004) Modelling the interpretation of novel compounds. In: ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings. Frontiers in Artificial Intelligence and Applications . IOS Press, ESP, pp. 1053-1054. ISBN 9781586034528

Full text not available from this repository.

Abstract

The understanding of novel compounds is a special case in which we can explore the deep generativity of natural language understanding. We report a model, PUNC, which captures the comprehension of novel noun-noun compounds. The model constructs multiple interpretations for a given compound, ranking these by their overall acceptability, using the key constraints of diagnosticity, plausibility and informativeness. We present a sensitivity analysis of the model's key variables, demonstrating a graceful degradation in performance as the weightings to these variables are altered, thus vindicating the model's underlying theoretical principles.

Item Type: Contribution in Book/Report/Proceedings
Uncontrolled Keywords: /dk/atira/pure/subjectarea/asjc/1700/1702
Subjects:
Departments: Faculty of Science and Technology > Psychology
ID Code: 128362
Deposited By: ep_importer_pure
Deposited On: 19 Oct 2018 13:46
Refereed?: Yes
Published?: Published
Last Modified: 01 Jan 2020 10:51
URI: https://eprints.lancs.ac.uk/id/eprint/128362

Actions (login required)

View Item View Item