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.
@article{arxiv.2201.01837,
title = {Frame Shift Prediction},
author = {Zheng-Xin Yong and Patrick D. Watson and Tiago Timponi Torrent and Oliver Czulo and Collin F. Baker},
journal= {arXiv preprint arXiv:2201.01837},
year = {2022}
}