124 citations · 446 across the 25 of their papers we have counts for
Showing 2017Show all
3 papers · 1 filter
cs.CL2017★ 21 cited
An Exploration of Word Embedding Initialization in Deep-Learning Tasks
Tom Kocmi, Ondřej Bojar
Word embeddings are the interface between the world of discrete units of text processing and the continuous, differentiable world of neural networks. In this work, we examine vario…
cs.CL2017★ 124 cited
Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
Tom Kocmi, Ondrej Bojar
We examine the effects of particular orderings of sentence pairs on the on-line training of neural machine translation (NMT). We focus on two types of such orderings: (1) ensuring…
cs.CL2017★ 5 cited
LanideNN: Multilingual Language Identification on Character Window
Tom Kocmi, Ondřej Bojar
In language identification, a common first step in natural language processing, we want to automatically determine the language of some input text. Monolingual language identificat…