Deciphering foreign language by combining language models and context vectors

Authors:
Malte Nuhn;Arne Mauser;Hermann Ney
Affiliations:
RWTH Aachen University, Germany;RWTH Aachen University, Germany;RWTH Aachen University, Germany
Venue:
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Year:
2012

Citing 10
Cited 0

A vector space model for automatic indexing

Communications of the ACM
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Generalized algorithms for constructing statistical language models

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Learning a translation lexicon from monolingual corpora

ULA '02 Proceedings of the ACL-02 workshop on Unsupervised lexical acquisition - Volume 9
Introduction to Information Retrieval

Introduction to Information Retrieval
Attacking decipherment problems optimally with low-order N-gram models

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Discovering the linear writing order of a two-dimensional ancient hieroglyphic script

Artificial Intelligence
OpenFst: a general and efficient weighted finite-state transducer library

CIAA'07 Proceedings of the 12th international conference on Implementation and application of automata
A statistical model for lost language decipherment

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Deciphering foreign language

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we show how to train statistical machine translation systems on real-life tasks using only non-parallel monolingual data from two languages. We present a modification of the method shown in (Ravi and Knight, 2011) that is scalable to vocabulary sizes of several thousand words. On the task shown in (Ravi and Knight, 2011) we obtain better results with only 5% of the computational effort when running our method with an n-gram language model. The efficiency improvement of our method allows us to run experiments with vocabulary sizes of around 5,000 words, such as a non-parallel version of the VERBMOBIL corpus. We also report results using data from the monolingual French and English GIGAWORD corpora.