Frame Shift Prediction

01/05/2022

∙

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.

READ FULL TEXT

Frame Shift Prediction

(p,q)-frames in shift-invariant subspaces of mixed Lebesgue spaces L^p,q(R×R^d)

Long-frame-shift Neural Speech Phase Prediction with Spectral Continuity Enhancement and Interpolation Error Compensation

Interpretable Distribution Shift Detection using Optimal Transport

Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition

Bias in Automated Image Colorization: Metrics and Error Types

Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining

3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction

Frame Shift Prediction

Related Research

(p,q)-frames in shift-invariant subspaces of mixed Lebesgue spaces L^p,q(R×R^d)

Long-frame-shift Neural Speech Phase Prediction with Spectral Continuity Enhancement and Interpolation Error Compensation

Interpretable Distribution Shift Detection using Optimal Transport

Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition

Bias in Automated Image Colorization: Metrics and Error Types

Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining

3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction