REAL

Towards a Robuster Interpretive Parsing

Biró, Tamás (2013) Towards a Robuster Interpretive Parsing. JOURNAL OF LOGIC LANGUAGE AND INFORMATION, 22 (2). pp. 139-172. ISSN 0925-8531 (print), 1572-9583 (online)

[img]
Preview
Text
off-print-10.1007_s10849-013-9172-x.pdf

Download (1MB) | Preview

Abstract

The input data to grammar learning algorithms often consist of overt forms that do not contain full structural descriptions. This lack of information may contribute to the failure of learning. Past work on Optimality Theory introduced Robust Interpretive Parsing (RIP) as a partial solution to this problem. We generalize RIP and suggest replacing the winner candidate with a weighted mean violation of the potential winner candidates. A Boltzmann distribution is introduced on the winner set, and the distribution’s parameter $T$ is gradually decreased. Finally, we show that GRIP, the Generalized Robust Interpretive Parsing Algorithm significantly improves the learning success rate in a model with standard constraints for metrical stress assignment.

Item Type: Article
Additional Information: 2013. április 9. "online first" módon publikálva.
Subjects: Q Science / természettudomány > QA Mathematics / matematika > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
SWORD Depositor: Teszt SWORD
Depositing User: Teszt SWORD
Date Deposited: 22 May 2013 06:57
Last Modified: 22 May 2013 06:57
URI: http://real.mtak.hu/id/eprint/5188

Actions (login required)

Edit Item Edit Item