Experiments | For each system, we used three different alignment heuristics (grow, grow-diag, grow-diag-final4) to obtain the final alignment results, and then constructed three different phrase tables . |
Experiments | In order to further analyze the translation results, we evaluated the above systems by examining the coverage of the phrase tables over the test phrases. |
Introduction | The first is based on phrase table multiplication (Cohn and Lapata 2007; Wu and Wang, 2007). |
Introduction | It multiples corresponding translation probabilities and lexical weights in source-pivot and pivot-target translation models to induce a new source-target phrase table . |
AL-SMT: Multilingual Setting | When (re-)training the models, two phrase tables are learned for each SMT model: one from the labeled data 11.. and the other one from pseudo-labeled data lU+ (which we call the main and auxiliary phrase tables respectively). |
Sentence Selection: Single Language Pair | Some of these fragments are the source language part of a phrase pair available in the phrase table , which we call regular phrases and denote their set by X £69 for a sentence 3. |
Sentence Selection: Single Language Pair | However, there are some fragments in the sentence which are not covered by the phrase table —possibly because of the OOVs (out-of-vocabulary words) or the constraints imposed by the phrase extraction algorithm — called X 800” for a sentence 5. |