← Authors

Ankur Bapna

28 papers · 2017–2023 · 10 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (10) 🐝 Cross-Pollinator (11) πŸ—ΊοΈ Taxonomy Completionist (47) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸƒ Academic Marathon (6) 🌟 Keyword Trendsetter Combo (3) 🀝 Dynamic Duo (19) πŸ† Grand Slam 🌱 Topic Pioneer πŸ”¬ Deep Specialist (13) 🧬 Topic Evolution πŸ† Keyword Champion (3) πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (110) πŸ”₯ Unstoppable (7) ⚑ Prolific Year (5) πŸ’Ž Century Club (28) ❓ The Questioner

Conferences

INTERSPEECH (8) EMNLP (5) ACL (4) ICLR (2) ICML (2) IJCNLP (2) NIPS (2) AAAI (1) COLING (1) NAACL (1)

Top co-authors

Orhan Firat (19) Yu Zhang (6) Sneha Kudugunta (5) Melvin Johnson (5) Yonghui Wu (5) Colin Cherry (4) Wolfgang Macherey (4) Isaac Caswell (4) Biao Zhang (4) Mia Chen (3)

Keywords

neural machine translation (9) transfer learning (5) multilingual translation (5) multilingual neural machine translation (4) domain adaptation (4) speech recognition (4) cross-lingual transfer (4) machine translation (4) representation learning (4) zero-shot translation (3) self-supervised learning (3) adapter layer (3) multilingual model (2) language model (2) zero-shot transfer (2) multilingual speech (2) model compression (2) language identification (2) automatic speech recognition (2) low-resource language (2)

Papers

Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models ICML 2023
LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus INTERSPEECH 2023
Label Aware Speech Representation Learning For Language Identification INTERSPEECH 2023
MADLAD-400: A Multilingual And Document-Level Large Audited Dataset NIPS 2023
PronScribe: Highly Accurate Multimodal Phonemic Transcription From Speech and Text INTERSPEECH 2023
XTREME-S: Evaluating Cross-lingual Speech Representations INTERSPEECH 2022
Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents ACL 2022
Scaling Laws for Neural Machine Translation ICLR 2022
Examining Scaling and Transfer of Language Model Architectures for Machine Translation ICML 2022
MAESTRO: Matched Speech Text Representations through Modality Matching INTERSPEECH 2022
Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation ACL 2022
Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation INTERSPEECH 2022
Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation ICLR 2021
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference EMNLP 2021
Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus COLING 2020
Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation ACL 2020
Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation AAAI 2020
Non-Parametric Adaptation for Neural Machine Translation NAACL 2019
Simple, Scalable Adaptation for Neural Machine Translation EMNLP 2019
Investigating Multilingual NMT Representations at Scale EMNLP 2019
Simple, Scalable Adaptation for Neural Machine Translation IJCNLP 2019
Investigating Multilingual NMT Representations at Scale IJCNLP 2019
Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model INTERSPEECH 2019
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism NIPS 2019
Revisiting Character-Based Neural Machine Translation with Capacity and Compression EMNLP 2018
Training Deeper Neural Machine Translation Models with Transparent Attention EMNLP 2018
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation ACL 2018
Towards Zero-Shot Frame Semantic Parsing for Domain Scaling INTERSPEECH 2017