A long time ago in the machine learning literature, the idea of incorporating a mechanism
inspired by the human visual system into neural networks was introduced. This idea is …

Machine translation (MT) is an important task in natural language processing (NLP), as it
automates the translation process and reduces the reliance on human translators. With the …

Transformer models have advanced the state of the art in many Natural Language
Processing (NLP) tasks. In this paper, we present a new Transformer architecture, Extended …

In recent years, larger and deeper models are springing up and continuously pushing state-
of-the-art (SOTA) results across various fields like natural language processing (NLP) and …

Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the
Transformer, learn powerful context-aware word representations through layered, multi …

This paper presents the first large-scale meta-evaluation of machine translation (MT). We
annotated MT evaluations conducted in 769 research papers published from 2010 to 2020 …

The Transformer architecture consists of self-attention and feed-forward networks (FFNs)
which can be viewed as key-value memories according to previous works. However, FFN …

Document-level MT models are still far from satisfactory. Existing work extend translation unit
from single sentence to multiple sentences. However, study shows that when we further …

Most of the existing models for document-level machine translation adopt dual-encoder
structures. The representation of the source sentences and the document-level contexts are …

Document-level machine translation manages to outperform sentence level models by a
small margin, but have failed to be widely adopted. We argue that previous research did not …