Asa Cooper Stickland
8 papers · 2019–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (5) π Academic Marathon (5) π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(20)
π₯
Unstoppable
(6)
β
The Questioner
Conferences
EMNLP (3)
EACL (2)
ICLR (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
parameter-efficient fine-tuning
(2)
adapter module
(2)
multilingual model
(2)
machine translation
(2)
transfer learning
(2)
parameter-efficient transfer learning
(1)
domain adaptation
(1)
multi-task learning
(1)
neural machine translation
(1)
pre-trained model
(1)
natural language understanding
(1)
multilingual machine translation
(1)
multilingual translation
(1)
parameter efficient
(1)
fisher information matrix
(1)
cross-lingual transfer
(1)
fisher information
(1)
noise robustness
(1)
posterior distribution
(1)
data augmentation
(1)
Papers
The Reversal Curse: LLMs trained on βA is Bβ fail to learn βB is Aβ
ICLR 2024
Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining
EACL 2023
When does Parameter-Efficient Transfer Learning Work for Machine Translation?
EMNLP 2022
Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation
EACL 2021
Regularising Fisher Information Improves Cross-lingual Generalisation
EMNLP 2021
Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters
EMNLP 2021
Deep Transformers with Latent Depth
NIPS 2020
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
ICML 2019