Title | ||
---|---|---|
cdec: a decoder, alignment, and learning framework for finite-state and context-free translation models |
Abstract | ||
---|---|---|
We present cdec, an open source framework for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based models, and models based on synchronous context-free grammars. Using a single unified internal representation for translation forests, the decoder strictly separates model-specific translation logic from general rescoring, pruning, and inference algorithms. From this unified representation, the decoder can extract not only the 1- or k-best translations, but also alignments to a reference, or the quantities necessary to drive discriminative training using gradient-based or gradient-free optimization techniques. Its efficient C++ implementation means that memory use and runtime performance are significantly better than comparable decoders. |
Year | Venue | Keywords |
---|---|---|
2010 | ACL (System Demonstrations) | translation forest,context-free translation model,statistical machine translation model,separates model-specific translation logic,unified representation,comparable decoder,k-best translation,efficient C,general rescoring,discriminative training,single unified internal representation |
DocType | Citations | PageRank |
Conference | 130 | 6.33 |
References | Authors | |
25 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
chris dyer | 1 | 5438 | 232.28 |
Jonathan Weese | 2 | 325 | 19.11 |
Hendra Setiawan | 3 | 202 | 14.83 |
Adam Lopez | 4 | 538 | 34.69 |
Ferhan Ture | 5 | 191 | 9.56 |
Vladimir Eidelman | 6 | 323 | 17.61 |
Juri Ganitkevitch | 7 | 659 | 32.71 |
Phil Blunsom | 8 | 3130 | 152.18 |
Philip Resnik | 9 | 4352 | 377.99 |