Frame shift is a cross-linguistic phenomenon in translation which results in corresponding pairs of linguistic material evoking different frames. The ability to predict frame shifts enables automatic creation of multilingual FrameNets through annotation projection. Here, we propose the Frame Shift Prediction task and demonstrate that graph attention networks, combined with auxiliary training, can learn cross-linguistic frame-to-frame correspondence and predict frame shifts.

翻译：框架转换是一种跨语言的翻译现象,它导致相应的语言材料配对引出不同的框架。 能够预测框架变换使得通过批注预测自动创建多语言框架网络。 在这里,我们提出框架变换预测任务,并展示图形关注网络,加上辅助培训,可以学习跨语言框架对框架的对应和预测框架变换。