Lattice-Based Minimum Error Rate Training Using Weighted Finite-State Transducers with Tropical Polynomial Weights

Aurelien Waite, Graeme Blackwood, William Byrne


Anthology ID:
W12-6219
Volume:
Proceedings of the 10th International Workshop on Finite State Methods and Natural Language Processing
Month:
July
Year:
2012
Address:
Donostia–San Sebastián
Editors:
Iñaki Alegria, Mans Hulden
Venue:
FSMNLP
SIG:
SIGFSM
Publisher:
Association for Computational Linguistics
Note:
Pages:
116–125
Language:
URL:
https://aclanthology.org/W12-6219
DOI:
Bibkey:
Cite (ACL):
Aurelien Waite, Graeme Blackwood, and William Byrne. 2012. Lattice-Based Minimum Error Rate Training Using Weighted Finite-State Transducers with Tropical Polynomial Weights. In Proceedings of the 10th International Workshop on Finite State Methods and Natural Language Processing, pages 116–125, Donostia–San Sebastián. Association for Computational Linguistics.
Cite (Informal):
Lattice-Based Minimum Error Rate Training Using Weighted Finite-State Transducers with Tropical Polynomial Weights (Waite et al., FSMNLP 2012)
Copy Citation:
PDF:
https://aclanthology.org/W12-6219.pdf