Phrasal: A Toolkit for New Directions in Statistical Machine Translation

By Spence Green, Daniel Matthew Cer, Christopher D. Manning. 2014

47 citations recorded by the source corpus.

We present a new version of Phrasal, an open-source toolkit for statistical phrasebased machine translation. This revision includes features that support emerging research trends such as (a) tuning with large feature sets, (b) tuning on large datasets like thebitext, and(c)web-basedinteractivemachine translation. A direct comparison with Moses shows favorable results in terms of decoding speed and tuning time.

Subfields: Artificial Intelligence, Molecular Biology, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Machine Translation

Citations in the corpus

Models and Inference for Prefix-Constrained Machine Translation (2016, methodology): “The phrase-based systems are built with Phrasal (Green et al., 2014), an open source toolkit.”
Edinburgh Research Explorer Stanford University's Submissions to the WMT 2014 Translation Task (2014, methodology): “We trained 512 word classes on the constrained German data using the predictive one-sided class model of Whittaker and Woodland (2001) with the parallelized clustering algorithm of Uszkoreit and Brants (2008) by Green et al. (2014a).”
Human Effort and Machine Learnability in Computer Aided Translation (2014, methodology): “The default Phrasal search algorithm is cube pruning (Huang and Chiang, 2007).”
Predictive translation memory: a mixed-initiative system for human language translation (2014, methodology): “The UI design required considerable backend engineering to support real-time suggestion updating [20].”