Phrase Pair Refinement and Parameterization | This refinement can be applied before finding the phrase pair with maximum probability (Line 12 in Figure 2) so that the duplicate words do not affect the calculation of translation probability of phrase pair. |
Phrase Pair Refinement and Parameterization | 5.2 Translation Probability Estimation |
Phrase Pair Refinement and Parameterization | It is well known that in the phrase-based SMT there are four translation probabilities and the reordering probability for each phrase pair. |
Probabilistic Bilingual Lexicon Acquisition | After using the log-likelihood-ratios algorithm2, we obtain a probabilistic bilingual lexicon with bidirectional translation probabilities from the out-of-domain data. |
Probabilistic Bilingual Lexicon Acquisition | It should be noted that there is no translation probability in this lexicon. |
Probabilistic Bilingual Lexicon Acquisition | In order to assign probabilities to each entry, we apply the Corpus Translation Probability which used in (Wu et al., 2008): given an in-domain source language monolingual data, we translate this data with the phrase-based model trained on the out-of-domain News data, the in-domain lexicon and the in-domain target language monolingual data (for language model estimation). |
Conclusion and Future Work | cinct phrase table with more accurate translation probabilities . |
Conclusion and Future Work | In future work, we will also introduce incremental learning for phase pair extraction inside a domain, which means using the current translation probabilities already obtained as the base measure of sampling parameters for the upcoming domain. |
Experiment | Pialign-adaptive: Alignment and phrase pairs extraction are same to Pialign-batch, while translation probabilities are estimated by the adaptive method with monolingual topic information (Su et al., 2012). |
Experiment | The method established the relationship between the out-of-domain bilingual corpus and in-domain monolingual corpora via topic distribution to estimate the translation probability . |
Experiment | In the phrase table combination process, the translation probability of each phrase pair is estimated by the Hier-combin and the other features are also linearly combined by averaging |
Hierarchical Phrase Table Combination | For example in Figure 2 (a), the ith phrase pair (6,, fi> appears only in the domain 1 and domain 2, so its translation probability can be calculated by substituting Equation (3) with Equation (2): |
Hierarchical Phrase Table Combination | Algorithm 1 Translation Probabilities Estimation Input: , ti , ijase, 03, T9, dj and sj Output: The translation probabilities for each pair 1: for all phrase pair (6,, fi> do 2: Initialize the P((ei, = 0 and w,- = 1 3: for all domain (Ej, Fj> such that l g j g |
Phrase Pair Extraction with Unsupervised Phrasal ITGs | Translation probabilities of ITG phrasal align- |
Related Work | In principle, our architecture can support all mixture operations that (Razmara et al., 2012) describe, plus additional ones such as forms of instance weighting, which are not possible after the translation probabilities have been computed. |
Translation Model Architecture | Traditionally, the phrase translation probabilities p(§|f) and p(f|§) are estimated through un-smoothed maximum likelihood estimation (MLE). |
Translation Model Architecture | The word translation probabilities w (t,- | 33) are de- |
DNN for word alignment | where Plegc is the lexical translation probability and Pd is the jump distance distortion probability. |
DNN for word alignment | In the classic HMM word alignment model, context is not considered in the lexical translation probability . |
Training | our model from raw sentence pairs, they are too computational demanding as the lexical translation probabilities must be computed from neural networks. |