Transducer Disambiguation with Sparse Topological Features

Download: poster.

Transducer Disambiguation with Sparse Topological Features” by Gonzalo Iglesias, Adrià de Gispert, and William Byrne. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015.

Abstract

We describe a simple and efficient algorithm to disambiguate non-functional weighted finite state transducers (WFST), 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 with the use of a novel tropical sparse tuple vector semiring. We empirically prove that our algorithm is more efficient than previous work in a PoS-tagging disambiguation task. Also, we use our method to rescore very large translation lattices with a bilingual neural network language model, obtaining gains in line with the literature.

Download: poster.

BibTeX entry:

@inproceedings{emnlp15:transdisamb,
   author = {Gonzalo Iglesias and Adri{\`a} de Gispert and William Byrne},
   title = {Transducer Disambiguation with Sparse Topological Features},
   booktitle = {Proceedings of the 2015 Conference on Empirical Methods in
	Natural Language Processing},
   year = {2015},
   url = {http://www.aclweb.org/anthology/D/D15/D15-1273.pdf}
}

Back to Bill Byrne publications.