Large language models (LLMs) are known to effectively perform tasks by s...
Pre-trained language models (PLMs) have accomplished impressive achievem...
Direct speech-to-speech translation (S2ST) is among the most challenging...
Numerous recent work on unsupervised machine translation (UMT) implies t...
We introduce a generic seq2seq parsing framework that casts constituency...
We introduce a novel top-down end-to-end formulation of document-level
d...
We propose Differentiable Window, a new neural module and general purpos...
We propose a novel constituency parsing model that casts the parsing pro...
Recent unsupervised machine translation (UMT) systems usually employ thr...
Incorporating hierarchical structures like constituency trees has been s...
A common approach to improve neural machine translation is to invent new...