Alignment Link Confidence Measure | We combine the HMM alignment, the BM alignment and the MaXEnt alignment (ME) using the above link selection algorithm. |
Alignment Link Confidence Measure | Figure 3 shows such an example, where alignment errors in the MaXEnt alignment are shown with dotted lines. |
Improved MaXEnt Aligner with Confidence-based Link Filtering | In addition to the alignment combination, we also improve the performance of the MaXEnt aligner through confidence-based alignment link filtering. |
Improved MaXEnt Aligner with Confidence-based Link Filtering | Here we select the MaXEnt aligner because it has |
Introduction | In section 4 we show how to improve a MaXEnt word alignment quality by removing low confidence alignment links, which also leads to improved translation quality as shown in section 5. |
Related Work | Regarding word alignment combination, in addition to the commonly used ”intersection-union-refine” approach (Och and Ney, 2003), (Ayan and Dorr, 2006b) and (Ayan et al., 2005) combined alignment links from multiple word alignment based on a set of linguistic and alignment features within the MaXEnt framework or a neural net model. |
Sentence Alignment Confidence Measure | HMM 54.72 -0.710 BM 62.53 -0.699 MaxEnt 69.26 -0.699 |
Sentence Alignment Confidence Measure | We randomly selected 512 Chinese-English (CE) sentence pairs and generated word alignment using the MaxEnt aligner (Ittycheriah and Roukos, 2005). |
Sentence Alignment Confidence Measure | For each sentence pair in the CE test set, we calculate the confidence scores of the HMM alignment, the Block Model alignment and the MaXEnt alignment, then select the alignment with the highest confidence score. |
Translation | We extract phrase translation tables from the baseline MaXEnt word alignment as well as the alignment with confidence-based link filtering, then translate the test set with each phrase translation table. |
Consensus Decoding Algorithms | The standard Viterbi decoding objective is to find 6* = arg maxe A - 6( f, e). |
Consensus Decoding Algorithms | 6 = arg maxe EP(e/|f) [8(6; (3’)] arg maxe Z P(e’|f) - 8(6; 6’) |
Consensus Decoding Algorithms | arg maerE EP(e’|f) [3(6; 6/” = arg maxe Z P(e/|f) - ij'(€) ° ¢j(el) e’EE j |