Ondřej Dušek

53 papers · 2013–2026 · 8 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) 🏃 Academic Marathon (12) 🐝 Cross-Pollinator (5) 🌈 Renaissance Researcher (9) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (73) 🏆 Keyword Champion (3) 🔬 Deep Specialist (13) 👥 Mega-Team (77) 🗃️ Keyword Collector (205) 📈 Trend Setter 🔥 Unstoppable (6) 💎 Century Club (51) ⚡ Prolific Year (8) ❓ The Questioner (2)

Conferences

EMNLP (19) ACL (14) EACL (6) IJCNLP (6) NAACL (4) INTERSPEECH (2) AACL (1) COLING (1)

Top co-authors

Verena Rieser (9) Mateusz Lango (9) Zdeněk Kasner (8) Ioannis Konstas (7) Patricia Schmidtova (6) Vojtěch Hudeček (6) Saad Mahamood (6) Sourabrata Mukherjee (5) Xinnuo Xu (5) Simone Balloccu (4)

Research topics

Keywords

large language model (8) natural language generation (8) dialogue system (7) data-to-text generation (6) human evaluation (6) task-oriented dialogue (5) evaluation metrics (5) language model (4) text style transfer (4) conversational agent (3) pretrained language model (3) transfer learning (3) sentiment transfer (3) text generation (3) bleu score (3) pre-trained language model (2) machine translation (2) zero-shot learning (2) discrete latent variable (2) sequence classification (2)

Papers

LLMs as Span Annotators: A Comparative Study of LLMs and Humans EACL 2026

AnimatedLLM: Explaining LLMs with Interactive Visualizations EACL 2026

SRS-Stories: Vocabulary-constrained multilingual story generation for language learning EMNLP 2025

Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics? NAACL 2025

Pretraining Language Models with LoRA and Artificial Languages EMNLP 2025

You are an LLM teaching a smaller model everything you know: Multi-task pretraining of language models with LLM-designed study plans EMNLP 2025

Real-World Summarization: When Evaluation Reaches Its Limits EMNLP 2025

Can Large Language Models Personalize Dialogues to Generational Styles? EMNLP 2025

LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators EMNLP 2025

ReproHum #0669-08: Reproducing Sentiment Transfer Evaluation ACL 2025

Ask the experts: sourcing a high-quality nutrition counseling dataset through Human-AI collaboration EMNLP 2024

Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs EACL 2024

Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach EMNLP 2024

Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation ACL 2024

Teaching LLMs at Charles University: Assignments and Activities ACL 2024

LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems NAACL 2024

ReproHum #0043-4: Evaluating Summarization Models: investigating the impact of education and language proficiency on reproducibility COLING 2024

UFAL-ULD at BLP-2023 Task 1: Violence Detection in Bangla Text EMNLP 2023

Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation EMNLP 2023

TabGenie: A Toolkit for Table-to-Text Generation ACL 2023

Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models EACL 2023

Polite Chatbot: A Text Style Transfer Application EACL 2023

Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP EACL 2023

UFAL-ULD at BLP-2023 Task 2 Sentiment Classification in Bangla Text EMNLP 2023

Low-Resource Text Style Transfer for Bangla: Data & Models EMNLP 2023

Learning Interpretable Latent Dialogue Actions With Less Supervision AACL 2022

Neural Pipeline for Zero-Shot Data-to-Text Generation ACL 2022

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code EMNLP 2022

Learning Interpretable Latent Dialogue Actions With Less Supervision IJCNLP 2022

GPT-2-based Human-in-the-loop Theatre Play Script Generation NAACL 2022

MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization EMNLP 2021

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics ACL 2021

Shades of BLEU, Flavours of Success: The Case of MultiWOZ ACL 2021

Discovering Dialogue Slots with Weak Supervision ACL 2021

AggGen: Ordering and Aggregating while Generating ACL 2021

AggGen: Ordering and Aggregating while Generating IJCNLP 2021

Discovering Dialogue Slots with Weak Supervision IJCNLP 2021

Shades of BLEU, Flavours of Success: The Case of MultiWOZ IJCNLP 2021

The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics IJCNLP 2021

AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models EMNLP 2021

SpeedySpeech: Efficient Neural Speech Synthesis INTERSPEECH 2020

Expand and Filter: CUNI and LMU Systems for the WNGT 2020 Duolingo Shared Task ACL 2020

One Model, Many Languages: Meta-Learning for Multilingual Text-to-Speech INTERSPEECH 2020

Fact-based Content Weighting for Evaluating Abstractive Summarisation ACL 2020

Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity EMNLP 2018

A Knowledge-Grounded Multimodal Search-Based Conversational Agent EMNLP 2018

Neural Response Ranking for Social Conversation: A Data-Efficient Approach EMNLP 2018

RankME: Reliable Human Ratings for Natural Language Generation NAACL 2018

Why We Need New Evaluation Metrics for NLG EMNLP 2017

Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings ACL 2016

Training a Natural Language Generator From Unaligned Data IJCNLP 2015

Training a Natural Language Generator From Unaligned Data ACL 2015

Robust multilingual statistical morphological generation models ACL 2013