Discussions | Ideally, a perfect combination of feature functions divides the correct and incorrect candidate phrase pairs within a parallel sentence into two ordered separate sets. |
Experimental Results | The training corpus consists of 40K Chinese-English parallel sentences in travel domain with to- |
Features | We will define a confidence metric to estimate how reliably the model can align an n-gram in one side to a phrase on the other side given a parallel sentence . |
Experimental Setup | 7Note that the although the corpora here are derived from a parallel corpus, there are no parallel sentences . |
Experimental Setup | 10These corpora contain no parallel sentences . |
Experimental Setup | For English-Arabic, we extract a lexicon from 100k parallel sentences of UN parallel corpora by running the HMM intersected alignment model (Liang et al., 2008), adding (3, t) to the lexicon if s was aligned to t at least three times and more than any other word. |