Marco Cognetta
9 papers · 2018–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (13) π Academic Marathon (7) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (29)
π
Conference Polyglot
(6)
π§
Keyword Pioneer
π
Keyword Champion
(3)
Conferences
EMNLP (3)
NAACL (2)
ACL (1)
COLING (1)
EACL (1)
IJCNLP (1)
Top co-authors
Keywords
byte-pair encoding
(3)
korean language
(2)
semantic equivalence
(2)
probabilistic finite automata
(2)
byte pair encoding
(2)
neural machine translation
(2)
infix probability
(2)
reinforcement learning
(2)
regex generation
(2)
natural language processing
(2)
machine translation
(2)
subword tokenization
(2)
deep neural network
(2)
morphological analysis
(1)
regular expression
(1)
uniform sampling
(1)
parameter efficiency
(1)
deep learning
(1)
context-free grammar
(1)
probabilistic context-free grammar
(1)
Papers
Jamo-Level Subword Tokenization in Low-Resource Korean Machine Translation
NAACL 2025
Distributional Properties of Subword Regularization
EMNLP 2024
An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
NAACL 2024
Two Counterexamples to Tokenization and the Noiseless Channel
COLING 2024
Parameter-Efficient Korean Character-Level Language Modeling
EACL 2023
SoftRegex: Generating Regex from Natural Language Descriptions using Softened Regex Equivalence
EMNLP 2019
Online Infix Probability Computation for Probabilistic Finite Automata
ACL 2019
SoftRegex: Generating Regex from Natural Language Descriptions using Softened Regex Equivalence
IJCNLP 2019
Incremental Computation of Infix Probabilities for Probabilistic Finite Automata
EMNLP 2018