Passive-Aggressive for On-Line Learning in Statistical Machine Translation

摘要

New variations on the application of the passive-aggressive algorithm to statistical machine translation are developed and compared to previously existing approaches. In online adaptation, the system needs to adapt to real-world changing scenarios, where training and tuning only take place when the system is set-up for the first time. Post-edit information, as described by a given quality measure, is used as valuable feedback within the passive-aggressive framework, adapting the statistical models on-line. First, by modifying the translation model parameters, and alternatively, by adapting the scaling factors present in state-of-the-art SMT systems. Experimental results show improvements in translation quality by allowing the system to learn on a sentence-by-sentence basis.