Collaborative decoding: partial hypothesis re-ranking using translation consensus between decoders
Year: 2009
Type: conference-paper
Abstract: This paper presents collaborative decoding (co-decoding), a new method to improve machine translation accuracy by leveraging translation consensus between multiple machine translation decoders. Different from system combination and MBR decoding, which post-process the n-best lists or word lattice of machine translation decoders, in our method multiple machine translation decoders collaborate by exchanging partial translation results. Using an iterative decoding approach, n-gram agreement statistics between translations of multiple decoders are employed to re-rank both full and partial hypothesis explored in decoding. Experimental results on data sets for NIST Chinese-to-English machine translation task show that the co-decoding method can bring significant improvements to all baseline decoders, and the outputs from co-decoding can be used to further improve the result of system combination.
Authors: Mu Li, Nan Duan, Dongdong Zhang, Chi-Ho Li, Ming Zhou
Institutions: Microsoft Research Asia (China), Tianjin University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W2117164663
