Experiments | As an example, while our probabilistic HR-SCFG maintains a separate joint phrase-pair emission distribution per nonterminal, the smoothing features (a) above assess the conditional translation of surface phrases irrespective of any notion of recursive translation structure. |
Introduction | As Hiero uses a single nonterminal and concentrates on overcoming translation lexicon sparsity, it barely explores the recursive nature of translation past the lexical level. |
Introduction | By advancing from structures which mimic linguistic syntax, to learning linguistically aware latent recursive structures targeting translation, we achieve significant improvements in translation quality for 4 different language pairs in comparison with a strong hierarchical translation baseline. |
Joint Translation Model | Figure 2: Recursive Reordering Grammar rule categories; A, B, C non—terminals; oz, fl source and target strings respectively. |
Joint Translation Model | structural part and their associated probabilities define a model 19(0) over the latent variable 0 determining the recursive , reordering and phrase-pair segmenting structure of translation, as in Figure 4. |
Learning Translation Structure | We aim to induce a recursive translation structure explaining the joint generation of the source and target |
Training algorithm | each model parameter over sentence Wl in document d in the training corpus D. For the WORD-PREDICTOR and the SEMANTIZER, the number of possible semantic annotation sequences is exponential, we use forward-backward recursive formulas that are similar to those in hidden Markov models to compute the expected counts. |
Training algorithm | In M-step, the recursive linear interpolation scheme (Jelinek and Mercer, 1981) is used to obtain a smooth probability estimate for each model component, WORD-PREDICTOR, TAGGER, and CONSTRUCTOR. |
Training algorithm | The recursive mixing scheme is the standard one among relative frequency estimates of different orders k = 0, - - - ,n as explained in (Chelba and J elinek, 2000). |