Augmenting Phrase Table by Employing Lexicons for Pivot-based SMT
This work addresses data sparsity problems in machine translation for language pairs with limited direct data, though it is incremental as it builds on existing pivot-based methods.
The paper tackles the phrase sparsity and error compounding issues in pivot-based statistical machine translation by augmenting the phrase table with a word lexicon model and proposing a pruning method that considers both source and target phrasal coverage. Experimental results show that this approach significantly outperforms conventional pruning methods and improves translation performance in Chinese-to-Japanese translation using English as a pivot language.
Pivot language is employed as a way to solve the data sparseness problem in machine translation, especially when the data for a particular language pair does not exist. The combination of source-to-pivot and pivot-to-target translation models can induce a new translation model through the pivot language. However, the errors in two models may compound as noise, and still, the combined model may suffer from a serious phrase sparsity problem. In this paper, we directly employ the word lexical model in IBM models as an additional resource to augment pivot phrase table. In addition, we also propose a phrase table pruning method which takes into account both of the source and target phrasal coverage. Experimental result shows that our pruning method significantly outperforms the conventional one, which only considers source side phrasal coverage. Furthermore, by including the entries in the lexicon model, the phrase coverage increased, and we achieved improved results in Chinese-to-Japanese translation using English as pivot language.