Do we need bigram alignment models? On the effect of alignment quality on transduction accuracy in G2P

Steffen Eger. Do we need bigram alignment models? On the effect of alignment quality on transduction accuracy in G2P. In Lluís Màrquez, Chris Callison-Burch, Jian Su, Daniele Pighin, Yuval Marton, editors, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015. pages 1175-1185, The Association for Computational Linguistics, 2015. [doi]

Abstract

Abstract is missing.