← Authors

Nikolay Bogoychev

26 papers · 2016–2024 · 5 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (8) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (48) 🌍 Conference Polyglot (5) 🏃 Academic Marathon (8) 🔬 Deep Specialist (17) 🤝 Dynamic Duo (17) 🧬 Topic Evolution 🗃️ Keyword Collector (108) ❓ The Questioner ⚡ Prolific Year (5) 💎 Century Club (26) 🔥 Unstoppable (7) 📈 Trend Setter

Conferences

EMNLP (13) ACL (9) NAACL (2) EACL (1) IJCNLP (1)

Top co-authors

Kenneth Heafield (17) Alham Fikri Aji (8) Pinzhen Chen (8) Roman Grundkiewicz (7) Ulrich Germann (6) Alexandra Birch (5) Jelmer van der Linde (4) Antonio Valerio Miceli Barone (3) Sidharth Kashyap (3) Maximiliana Behnke (3)

Keywords

neural machine translation (17) model compression (7) machine translation (6) knowledge distillation (4) stochastic gradient descent (3) model quantization (3) efficient inference (3) distributed training (3) latency optimization (2) constrained decoding (2) teacher-student training (2) language model (2) transfer learning (2) model convergence (2) transformer architecture (2) distributed learning (2) model pruning (2) gradient compression (2) throughput optimization (2) transformer model (2)

Papers

The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics NAACL 2024
Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca EACL 2024
Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting EMNLP 2023
An Open Dataset and Model for Language Identification ACL 2023
Findings of the WMT 2022 Shared Task on Efficient Translation EMNLP 2022
Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice ACL 2022
Edinburgh’s Submission to the WMT 2022 Efficiency Task EMNLP 2022
Not all parameters are born equal: Attention is mostly what you need EMNLP 2021
The University of Edinburgh’s English-German and English-Hausa Submissions to the WMT21 News Translation Task EMNLP 2021
Efficient Machine Translation with Model Pruning and Quantization EMNLP 2021
TranslateLocally: Blazing-fast translation running on the local CPU EMNLP 2021
The Highs and Lows of Simple Lexical Domain Adaptation Approaches for Neural Machine Translation EMNLP 2021
In Neural Machine Translation, What Does Transfer Learning Transfer? ACL 2020
Parallel Sentence Mining by Constrained Decoding ACL 2020
Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task EMNLP 2020
Edinburgh’s Submissions to the 2020 Machine Translation Efficiency Task ACL 2020
Character Mapping and Ad-hoc Adaptation: Edinburgh’s IWSLT 2020 Open Domain Translation System ACL 2020
From Research to Production and Back: Ludicrously Fast Neural Machine Translation EMNLP 2019
The University of Edinburgh’s Submissions to the WMT19 News Translation Task ACL 2019
Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training EMNLP 2019
Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training IJCNLP 2019
Similar Minds Post Alike: Assessment of Suicide Risk Using a Hybrid Model NAACL 2019
Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation EMNLP 2018
Marian: Fast Neural Machine Translation in C++ ACL 2018
The University of Edinburgh’s Submissions to the WMT18 News Translation Task EMNLP 2018
N-gram language models for massively parallel devices ACL 2016