Janghoon Han
8 papers · 2021–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (27) π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
ACL (4)
EMNLP (2)
ICLR (1)
NAACL (1)
Top co-authors
Keywords
beam search
(2)
language model
(2)
transfer learning
(2)
instruction tuning
(2)
model calibration
(1)
text generation
(1)
neural text generation
(1)
dialogue state tracking
(1)
temporal alignment
(1)
training efficiency
(1)
zero-shot generalization
(1)
multi-turn dialogue
(1)
negative mining
(1)
siamese network
(1)
response selection
(1)
temporal knowledge
(1)
multilingual model
(1)
retrieval-based dialogue
(1)
joint goal accuracy
(1)
knowledge updating
(1)
Papers
Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks
EMNLP 2024
Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning
ACL 2024
Efficient Dynamic Hard Negative Sampling for Dialogue Selection
ACL 2024
Local Temperature Beam Search: Avoid Neural Text DeGeneration via Enhanced Calibration
ACL 2023
BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-ranking
ACL 2023
TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models
EMNLP 2022
Towards Continual Knowledge Learning of Language Models
ICLR 2022
Fine-grained Post-training for Improving Retrieval-based Dialogue Systems
NAACL 2021