Dimitra Gkatzia
14 papers · 2014–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) 🌍 Conference Polyglot (5) 🏃 Academic Marathon (11) 🌉 Interdisciplinary Bridge
🐣
Hot Topic Early Bird
🗺️
Taxonomy Completionist
(22)
🌈
Renaissance Researcher
(5)
👥
Mega-Team
(77)
🧬
Topic Evolution
❓
The Questioner
(2)
🔥
Unstoppable
(5)
💎
Century Club
(13)
Conferences
ACL (4)
EACL (4)
EMNLP (4)
COLING (1)
INTERSPEECH (1)
Top co-authors
Research topics
Keywords
natural language generation
(3)
human evaluation
(3)
commonsense reasoning
(2)
transfer learning
(1)
data augmentation
(1)
paraphrase generation
(1)
machine translation
(1)
commonsense knowledge
(1)
text representation
(1)
privacy preservation
(1)
task-oriented dialogue
(1)
evaluation methodology
(1)
low-resource language
(1)
evaluation framework
(1)
machine learning
(1)
model evaluation
(1)
language model
(1)
human-ai collaboration
(1)
text embedding
(1)
natural language processing
(1)
Papers
LLMs as Span Annotators: A Comparative Study of LLMs and Humans
EACL 2026
Participatory Design for Positive Impact: Behind the Scenes of Three NLP Projects
ACL 2025
ReproHum #0712-01: Reproducing Human Evaluation of Meaning Preservation in Paraphrase Generation
COLING 2024
Automated Human-Readable Label Generation in Open Intent Discovery
INTERSPEECH 2024
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
EACL 2023
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
EMNLP 2022
Task2Dial: A Novel Task and Dataset for Commonsense-enhanced Task-based Dialogue Grounded in Documents
ACL 2022
Most NLG is Low-Resource: here’s what we can do about it
EMNLP 2022
It’s Commonsense, isn’t it? Demystifying Human Evaluations in Commonsense-Enhanced NLG Systems
EACL 2021
CAPE: Context-Aware Private Embeddings for Private Language Learning
EMNLP 2021
Natural Language Generation enhances human decision-making with uncertain information
ACL 2016
From the Virtual to the RealWorld: Referring to Objects in Real-World Spatial Scenes
EMNLP 2015
Comparing Multi-label Classification with Reinforcement Learning for Summarisation of Time-series Data
ACL 2014
Finding middle ground? Multi-objective Natural Language Generation from time-series data
EACL 2014