1 citations · 1 across the 3 of their papers we have counts for
8 papers
Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice
Andreas Grivas, Nikolay Bogoychev, Adam Lopez
Classifiers in natural language processing (NLP) often have a large number of output classes. For example, neural language models (LMs) and machine translation (MT) models both pre…
TranslateLocally: Blazing-fast translation running on the local CPU
Nikolay Bogoychev, Jelmer Van der Linde, Kenneth Heafield
Every day, millions of people sacrifice their privacy and browsing habits in exchange for online machine translation. Companies and governments with confidentiality requirements of…
The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation
Nikolay Bogoychev, Pinzhen Chen
Machine translation systems are vulnerable to domain mismatch, especially in a low-resource scenario. Out-of-domain translations are often of poor quality and prone to hallucinatio…
Not all parameters are born equal: Attention is mostly what you need
Nikolay Bogoychev
Transformers are widely used in state-of-the-art machine translation, but the key to their success is still unknown. To gain insight into this, we consider three groups of paramete…
Domain, Translationese and Noise in Synthetic Data for Neural Machine Translation
Nikolay Bogoychev, Rico Sennrich
The quality of neural machine translation can be improved by leveraging additional monolingual resources to create synthetic training data. Source-side monolingual data can be (for…
The University of Edinburgh's Submissions to the WMT19 News Translation Task
Rachel Bawden, Nikolay Bogoychev, Ulrich Germann +4
The University of Edinburgh participated in the WMT19 Shared Task on News Translation in six language directions: English-to-Gujarati, Gujarati-to-English, English-to-Chinese, Chin…