We propose an interactive-predictive neural machine translation framework for easier model personalization using reinforcement and imitation learning. During the interactive translation process, the user is asked for feedback on uncertain locations identified by the system. Responses are weak feedback in the form of "keep" and "delete" edits, and expert demonstrations in the form of "substitute" edits. Conditioning on the collected feedback, the system creates alternative translations via constrained beam search. In simulation experiments on two language pairs our systems get close to the performance of supervised training with much less human effort.
翻译:我们建议建立一个互动预测神经机翻译框架,以便通过强化和模仿学习,使模型个人化更加容易。在互动翻译过程中,用户被要求获得关于系统确定的不确定地点的反馈。 反应是“保持”和“删除”编辑形式的微弱反馈,以及“替代”编辑形式的专家演示。 根据所收集的反馈条件,系统通过限制光束搜索创建替代翻译。在对两种语言的模拟实验中,我们的系统接近监督培训的性能,而人的努力要少得多。