Search Results for author:
Found 5 papers, 1 papers with code
Quality at the Tail of Machine Learning Inference
The study unveils a counterintuitive revelation: deep learning inference quality exhibits fluctuations due to inference time.
Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation
Meanwhile, we force the conventional decoder to simulate the behaviors of the seer decoder via knowledge distillation.
Full-Sentence Models Perform Better in Simultaneous Translation Using the Information Enhanced Decoding Strategy
Besides, with the competence of the full-sentence model to encode the whole sentence, our decoding strategy can enhance the information maintained in the decoded states in real time.
Modeling Fluency and Faithfulness for Diverse Neural Machine Translation
Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution.
Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation
Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations.
