Abstract | On top of the pruning framework, we also propose a discriminative ITG alignment model using hierarchical phrase pairs , which improves both F-score and Bleu score over the baseline alignment system of GIZA++. |
Introduction | On top of the discriminative pruning method, we also propose a discriminative ITG alignment system using hierarchical phrase pairs . |
The DITG Models | Another is DITG with hierarchical phrase pairs (henceforth HP-DITG), which relaxes the l-to-l constraint by adopting hierarchical phrase pairs in Chiang (2007). |
The DITG Models | 6.2 DITG with Hierarchical Phrase Pairs |
The DITG Models | Wu (1997) proposes a bilingual segmentation grammar extending the terminal rules by including phrase pairs . |
The DPDI Framework | f len +elen Where #linksincon is the number of links which are inconsistent with the phrase pair according to some simpler alignment model (e.g. |
The DPDI Framework | 3 An inconsistent link connects a word Within the phrase pair to some word outside the phrase pair . |
Alignment | We refer to singleton phrases as phrase pairs that occur only in one sentence. |
Alignment | For these sentences, the decoder needs the singleton phrase pairs to produce an alignment. |
Alignment | Standard leaving-one-out assigns a fixed probability 04 to singleton phrase pairs . |
Introduction | The phrase translation table, which contains the bilingual phrase pairs and the corresponding translation probabilities, is one of the main components of an SMT system. |
Phrase Model Training | The translation probability of a phrase pair (1216) is estimated as |
Phrase Model Training | where CFA(f, 6) is the count of the phrase pair (f, 6) in the phrase-aligned training data. |
Phrase Model Training | We will refer to this model as the count model as we simply count the number of occurrences of a phrase pair . |
Bag-of-Words Vector Space Model | In the hierarchical phrase-based translation method, the translation rules are extracted by abstracting some words from an initial phrase pair (Chiang, 2005). |
Bag-of-Words Vector Space Model | Consider a rule with non-terminals on the source and target side; for a given instance of the rule (a particular phrase pair in the training corpus), the context will be the words instantiating the non-terminals. |
Bag-of-Words Vector Space Model | In turn, the context for the sub-phrases that instantiate the non-terminals will be the words in the remainder of the phrase pair . |