Maximiliana Behnke

5 papers · 2020–2022 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

EMNLP (4) ACL (1)

Top co-authors

Kenneth Heafield (5) Nikolay Bogoychev (3) Sidharth Kashyap (3) Jelmer van der Linde (2) Alham Fikri Aji (2) Graeme Nail (2) Roman Grundkiewicz (2) Qianqian Zhu (1) Svetlana Tchistiakova (1) Emmanouil-Ioannis Farsarakis (1)

Research topics

Deep Learning (5) Machine Learning (5) Natural Language Processing (5) Application Areas (5) Applications (5) Optimization & Theory (5) Architectures (2) Techniques (2) Learning Types (1)

Keywords

model compression (4) neural machine translation (3) model pruning (3) model quantization (3) transformer architecture (2) knowledge distillation (2) machine translation (2) inference optimization (2) inference efficiency (1) tensor core (1) inference latency (1) inference speed (1) encoder-decoder architecture (1) latency optimization (1) inference speedup (1) layer pruning (1) efficient translation (1) teacher-student training (1) attention pruning (1) attention head pruning (1)

Papers

Edinburgh’s Submission to the WMT 2022 Efficiency Task EMNLP 2022 Efficient Machine Translation with Model Pruning and Quantization EMNLP 2021 Pruning Neural Machine Translation for Speed Using Group Lasso EMNLP 2021 Edinburgh’s Submissions to the 2020 Machine Translation Efficiency Task ACL 2020 Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation EMNLP 2020