CUED Publications database

Transducer disambiguation with sparse topological features

Iglesias, G and De Gispert, A and Byrne, B (2015) Transducer disambiguation with sparse topological features. In: UNSPECIFIED pp. 2275-2280..

Full text not available from this repository.

Abstract

© 2015 Association for Computational Linguistics. We describe a simple and efficient algorithm to disambiguate non-functional weighted finite state transducers (WFSTs), i.e. to generate a new WFST that contains a unique, best-scoring path for each hypothesis in the input labels along with the best output labels. The algorithm uses topological features combined with a tropical sparse tuple vector semiring. We empirically show that our algorithm is more efficient than previous work in a PoS-tagging disambiguation task. We use our method to rescore very large translation lattices with a bilingual neural network language model, obtaining gains in line with the literature.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:43
Last Modified: 03 Aug 2017 03:13
DOI: