← Authors

David Samuel

18 papers · 2020–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (28) πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (5) 🧭 Keyword Pioneer 🐺 Lone Wolf (3) πŸ‘₯ Mega-Team (35) πŸ”₯ Unstoppable (6) ⚑ Prolific Year (6) πŸ’Ž Century Club (18) ❓ The Questioner πŸ—ƒοΈ Keyword Collector (70)

Conferences

EMNLP (6) ACL (4) CONLL (4) COLING (1) EACL (1) NAACL (1) NIPS (1)

Top co-authors

Lilja Øvrelid (7) Erik Velldal (4) Lucas Georges Gabriel Charpentier (3) Milan Straka (3) Andrey Kutuzov (3) Huiling You (2) Petter Mæhlum (2) Stephan Oepen (2) Vladislav Mikhailov (2) Samia Touileb (2)

Keywords

semantic parsing (4) multilingual nlp (3) language model (3) sentiment analysis (2) large language model (2) argument extraction (2) meaning representation (2) event extraction (2) graph-based parser (2) language modeling (2) graph-based parsing (2) masked language model (2) multilingual processing (1) text representation (1) in-context learning (1) parallel corpus (1) dependency parsing (1) structured prediction (1) synthetic datum (1) machine translation (1)

Papers

An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT) ACL 2025
NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark ACL 2025
More room for language: Investigating the effect of retrieval on language models NAACL 2024
It’s Difficult to Be Neutral – Human and LLM-based Sentiment Annotation of Patient Comments COLING 2024
GPT or BERT: why not both? CONLL 2024
BERTs are Generative In-Context Learners NIPS 2024
Tokenization with Factorized Subword Encoding ACL 2023
Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings CONLL 2023
Not all layers are equally as important: Every Layer Counts BERT CONLL 2023
Not all layers are equally as important: Every Layer Counts BERT EMNLP 2023
Trained on 100 million words and still in shape: BERT meets British National Corpus EACL 2023
Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings EMNLP 2023
Direct parsing to sentiment graphs ACL 2022
EventGraph: Event Extraction as Semantic Graph Parsing EMNLP 2022
EventGraph at CASE 2021 Task 1: A General Graph-based Approach to Protest Event Extraction EMNLP 2022
ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5 EMNLP 2021
ÚFAL at MRP 2020: Permutation-invariant Semantic Parsing in PERIN CONLL 2020
ÚFAL at MRP 2020: Permutation-invariant Semantic Parsing in PERIN EMNLP 2020