We present a linguistically-motivated algorithm for reconstructing nonlocal dependency in broad-coverage context-free parse trees derived from treebanks. We use an algorithm based...
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Fost...
We firstly describe an algebraic structure which serves as solid basis to quantitatively reason about information flows. We demonstrate how programs in form of partition of state...
Word alignment plays a crucial role in statistical machine translation. Word-aligned corpora have been found to be an excellent source of translation-related knowledge. We present...