In this technical report, we introduce Effidit (Efficient and Intelligen...
Probing is popular to analyze whether linguistic information can be capt...
Current practices in metric evaluation focus on one single dataset, e.g....
While GPT has become the de-facto method for text generation tasks, its
...
Computer-aided translation (CAT), the use of software to assist a human
...
Automatic machine translation is super efficient to produce translations...
Machine Translation Quality Estimation (QE) is a task of predicting the
...
Many efforts have been devoted to extracting constituency trees from
pre...
Recently many efforts have been devoted to interpreting the black-box NM...
Context gates are effective to control the contributions from the source...
Lexically constrained decoding for machine translation has shown to be
b...
Current Neural Machine Translation (NMT) employs a language-specific enc...