Yichao Du

Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement

2021 · arXiv (Cornell University)

End-to-end speech-to-text translation (E2E-ST) is becoming increasingly popular due to the potential of its less error propagation, lower latency, and fewer parameters. Given the triplet training corpus $\langle speech, transcription, translation\rangle$, the conventional high-quality E2E-ST …

Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer

2023 · arXiv (Cornell University)

Nearest Neighbor Machine Translation ($k$NN-MT) has achieved great success in domain adaptation tasks by integrating pre-trained Neural Machine Translation (NMT) models with domain-specific token-level retrieval. However, the reasons underlying its success have not been thoroughly …