论文信息 - MMT: New Open Source MT for the Translation Industry

MMT: New Open Source MT for the Translation Industry

MMT is a new open source machine translation software specifically addressing the needs of the translation industry. In this paper we describe its overall architecture and provide details about its major components. We report performance results on a multi-domain benchmark based on public data, on two translation directions, by comparing MMT against state-of-theart commercial and research phrase-based and neural MT systems.

[1] George F. Foster,et al. Batch Tuning Strategies for Statistical Machine Translation , 2012, NAACL.

[2] Christopher D. Manning,et al. Stanford Neural Machine Translation Systems for Spoken Language Domains , 2015, IWSLT.

[3] Franz Josef Och,et al. Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[4] Marcello Federico,et al. Broadcast news LM adaptation using contemporary texts , 2001, INTERSPEECH.

[5] Yoshua Bengio,et al. Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[6] Philipp Koehn,et al. Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[7] Noah A. Smith,et al. A Simple, Fast, and Effective Reparameterization of IBM Model 2 , 2013, NAACL.

[8] Philipp Koehn,et al. Scalable Modified Kneser-Ney Language Model Estimation , 2013, ACL.

[9] Marcello Federico,et al. Neural vs. Phrase-Based Machine Translation in a Multi-Domain Scenario , 2017, EACL.

[10] Ulrich Germann,et al. Sampling Phrase Tables for the Moses Statistical Machine Translation System , 2015, Prague Bull. Math. Linguistics.