Search Results for author:
Found 4 papers, 3 papers with code
Exploring the Importance of Source Text in Automatic Post-Editing for Context-Aware Machine Translation
They also highlight blind spots in automatic methods for targeted evaluation and demonstrate the need for human assessment to evaluate document-level translation quality reliably.
Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models
We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs).
Progressive Translation: Improving Domain Robustness of Neural Machine Translation with Intermediate Sequences
Furthermore, we introduce a full-permutation multi-task learning to alleviate the spurious causal relations from intermediate sequences to the target, which results from exposure bias.
On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
In experiments on three datasets with multiple test domains, we show that exposure bias is partially to blame for hallucinations, and that training with Minimum Risk Training, which avoids exposure bias, can mitigate this.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
