John Hewitt
17 papers · 2017–2025 · 5 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 ↓+5 more ↓ Show less ↑
🗺️ Taxonomy Completionist (36) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Bronze
🧬
Topic Evolution
🧭
Keyword Pioneer
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(89)
💎
Century Club · Bronze
Top co-authors
Research topics
Natural Language Processing
(13)
Machine Learning
(11)
Deep Learning
(10)
Artificial Intelligence
(9)
Core AI
(8)
Core Methods
(6)
Optimization & Theory · Machine Learning
(6)
Resources & Methods
(6)
Generation
(5)
Learning Types · Deep Learning
(5)
Applications
(4)
Architectures
(3)
Models
(3)
Optimization & Theory · Deep Learning
(3)
Learning Types · Machine Learning
(2)
Keywords
language model
(6)
word embedding
(4)
representation learning
(3)
text generation
(3)
cross-lingual transfer
(3)
sampling strategy
(2)
word translation
(2)
low-resource language
(2)
natural language inference
(2)
nucleus sampling
(2)
machine translation
(1)
masked language model
(1)
language modeling
(1)
multimodal learning
(1)
universal dependencies
(1)
interpretability
(1)
linear transformation
(1)
cross-lingual representation
(1)
abstraction
(1)
matrix completion
(1)
Papers
Position: We Can’t Understand AI Using our Existing Vocabulary
ICML 2025
Closing the Curious Case of Neural Text Degeneration
ICLR 2024
Backpack Language Models
ACL 2023
Character-Level Chinese Backpack Language Models
EMNLP 2023
Generating Text from Language Models
ACL 2023
JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset
EMNLP 2022
Truncation Sampling as Language Model Desmoothing
EMNLP 2022
Conditional probing: measuring usable information beyond a baseline
EMNLP 2021
Refining Targeted Syntactic Evaluation of Language Models
NAACL 2021
Finding Universal Grammatical Relations in Multilingual BERT
ACL 2020
RNNs can generate bounded hierarchical languages with optimal memory
EMNLP 2020
The EOS Decision and Length Extrapolation
EMNLP 2020
A Structural Probe for Finding Syntax in Word Representations
NAACL 2019
Designing and Interpreting Probes with Control Tasks
EMNLP 2019
A Distributional and Orthographic Aggregation Model for English Derivational Morphology
ACL 2018
Learning Translations via Images with a Massively Multilingual Image Dataset
ACL 2018
Learning Translations via Matrix Completion
EMNLP 2017