← Authors

Melvin Johnson

23 papers · 2018–2023 · 9 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (5) πŸƒ Academic Marathon (5) 🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (36) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (9) πŸ”¬ Deep Specialist (11) πŸ‘₯ Mega-Team (27) πŸ—ƒοΈ Keyword Collector (76) ⚑ Prolific Year (9) πŸ’Ž Century Club (23) πŸ”₯ Unstoppable (6) ❓ The Questioner (2)

Conferences

EMNLP (5) ACL (4) ICML (3) IJCNLP (3) NAACL (3) INTERSPEECH (2) AAAI (1) EACL (1) ICLR (1)

Top co-authors

Orhan Firat (9) Aditya Siddhant (7) Ankur Bapna (5) Sebastian Ruder (5) Jason Riesa (4) Mihir Kale (4) Henry Tsai (4) Colin Cherry (3) Wolfgang Macherey (3) Graham Neubig (3)

Keywords

cross-lingual transfer (6) neural machine translation (6) low-resource language (6) machine translation (5) multilingual language model (3) benchmark evaluation (3) multilingual model (3) sequence labeling (3) transfer learning (2) multilingual encoder (2) morphological prediction (2) speech translation (2) knowledge distillation (2) part-of-speech tagging (2) zero-shot transfer (2) model compression (2) multilingual nlp (2) speech recognition (2) document-level translation (2) attention mechanism (1)

Papers

XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages EMNLP 2023
The Unreasonable Effectiveness of Few-shot Learning for Machine Translation ICML 2023
Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models ICML 2023
Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents ACL 2022
XTREME-S: Evaluating Cross-lingual Speech Representations INTERSPEECH 2022
DOCmT5: Document-Level Pretraining of Multilingual Language Models NAACL 2022
Domain Curricula for Code-Switched MT at MixMT 2022 EMNLP 2022
Rethinking Embedding Coupling in Pre-trained Language Models ICLR 2021
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models? ACL 2021
MergeDistill: Merging Language Models using Pre-trained Distillation ACL 2021
Findings of the Shared Task on Machine Translation in Dravidian languages EACL 2021
HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints EMNLP 2021
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation EMNLP 2021
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models? IJCNLP 2021
MergeDistill: Merging Language Models using Pre-trained Distillation IJCNLP 2021
Explicit Alignment Objectives for Multilingual Bidirectional Encoders NAACL 2021
Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation AAAI 2020
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation ICML 2020
Massively Multilingual Neural Machine Translation NAACL 2019
Small and Practical BERT Models for Sequence Labeling EMNLP 2019
Direct Speech-to-Speech Translation with a Sequence-to-Sequence Model INTERSPEECH 2019
Small and Practical BERT Models for Sequence Labeling IJCNLP 2019
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation ACL 2018