Stephan Gouws

TL;DR: GNMT, Google's Neural Machine Translation system, is presented, which attempts to address many of the weaknesses of conventional phrase-based translation systems and provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delicited models.

TL;DR: The authors proposed the Universal Transformer model, which employs a self-attention mechanism in every recursive step to combine information from different parts of a sequence, and further employs an adaptive computation time (ACT) mechanism to dynamically adjust the number of times the representation of each position in a sequence is revised.

TL;DR: This paper proposed BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data.

TL;DR: Tensor2Tensor as mentioned in this paper is a library for deep learning models that is well-suited for neural machine translation and includes the reference implementation of the state-of-the-art Transformer model.

TL;DR: It is shown that bilingual embeddings learned using the proposed BilBOWA model outperform state-of-the-art methods on a cross-lingual document classification task as well as a lexical translation task on WMT11 data.