tailieunhanh - Báo cáo khoa học: "Learning Translation Consensus with Structured Label Propagation"

In this paper, we address the issue for learning better translation consensus in machine translation (MT) research, and explore the search of translation consensus from similar, rather than the same, source sentences or their spans. Unlike previous work on this topic, we formulate the problem as structured labeling over a much smaller graph, and we propose a novel structured label propagation for the task. | Learning Translation Consensus with Structured Label Propagation fShujie Liu Harbin Institute of Technology Harbin China shujieliu@mtlab . ỊChi-Ho Li ỊMu Li and ỊMing Zhou Microsoft Research Asia Beijing China chl muli mingzhou @ Abstract In this paper we address the issue for learning better translation consensus in machine translation MT research and explore the search of translation consensus from similar rather than the same source sentences or their spans. Unlike previous work on this topic we formulate the problem as structured labeling over a much smaller graph and we propose a novel structured label propagation for the task. We convert such graph-based translation consensus from similar source strings into useful features both for n-best output reranking and for decoding algorithm. Experimental results show that our method can significantly improve machine translation performance on both IWSLT and NIST data compared with a state-of-the-art baseline. 1 Introduction Consensus in translation has gained more and more attention in recent years. The principle of consensus can be sketched as a translation candidate is deemed more plausible if it is supported by other translation candidates. The actual formulation of the principle depends on whether the translation candidate is a complete sentence or just a span of it whether the candidate is the same as or similar to the supporting candidates and whether the supporting candidates come from the same or different MT system. This work has been done while the first author was visiting Microsoft Research Asia. Translation consensus is employed in those minimum Bayes risk MBR approaches where the loss function of a translation is defined with respect to all other translation candidates. That is the translation with the minimal Bayes risk is the one to the greatest extent similar to other candidates. These approaches include the work of Kumar and Byrne 2004 which re-ranks the n-best output of a MT