Abstract: Translation quality estimation (QE) technology aims to evaluate the quality of machine translations without reference translations. Currently, research on word-level QE mainly focuses on ...
Simultaneous machine translation (SiMT) aims to deliver real-time translations as a source language, spoken or written. Traditionally, this requires models that control when to “read” more of the ...
When it comes to teaching languages, the grammar-translation method has become the child nobody loves or wants to acknowledge. But is it really hell on toast? No, it ain’t. There, I said it. Leave it ...
Implementation of the following thesis project: Building Domain-Specific Sub-Models from Large Language Models using Pruning. Acknowledging the benefits of Wanda pruning method, which prunes LLMs ...
Clean and provvisory code base for USKI pre-training described in "Learning from Wrong Predictions in Low-Resource Neural Machine Translation" presented at LREC-COLING 2024. python3.7 train.py \ ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results