Philipp Dufter

20 papers · 2018–2025 · 9 conferences · across top CS/AI conferences

Achievements

+12 more ↓

🌈 Renaissance Researcher (7) 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (7) 🌍 Conference Polyglot (9) 🗺️ Taxonomy Completionist (41)

🗺️ Taxonomy Completionist (41) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🧬 Topic Evolution 🤝 Dynamic Duo (16) 👥 Mega-Team (29) 🗃️ Keyword Collector (81) 📈 Trend Setter 🔥 Unstoppable (5) 💎 Century Club (20) ❓ The Questioner ⚡ Prolific Year (8)

Conferences

EMNLP (7) NAACL (3) ACL (2) COLING (2) IJCNLP (2) CVPR (1) EACL (1) ECCV (1) ICLR (1)

Top co-authors

Hinrich Schütze (16) Masoud Jalili Sabet (4) Zhe Gan (3) Martin Schmitt (3) Yinfei Yang (3) Ayyoob Imani (3) Nora Kassner (2) Peter Grasch (2) Michael Cysou (2) Zirui Wang (2)

Keywords

multilingual nlp (5) gender bia (4) word alignment (4) multilingual embedding (3) word embedding (3) parallel corpus (3) typological research (2) cross-lingual transfer (2) static embedding (2) lexicon induction (2) contextualized embedding (2) masked language modeling (2) masked language model (2) language similarity (2) transfer learning (2) support vector machine (2) pretrained language model (2) transformer architecture (2) multimodal learning (1) feature learning (1)

Papers

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning ICLR 2025 Multimodal Autoregressive Pre-training of Large Vision Encoders CVPR 2025 "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training" ECCV 2024 An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language Models NAACL 2022 Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models EACL 2021 ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ACL 2021 Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs NAACL 2021 Wine is not v i n. On the Compatibility of Tokenizations across Languages EMNLP 2021 Graph Algorithms for Multiparallel Word Alignment EMNLP 2021 BERT Cannot Align Characters EMNLP 2021 Static Embeddings as Efficient Knowledge Bases? NAACL 2021 ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus IJCNLP 2021 SimAlign: High Quality Word Alignments Without Parallel Training Data Using Static and Contextualized Embeddings EMNLP 2020 Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention COLING 2020 Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations COLING 2020 Identifying Elements Essential for BERT’s Multilinguality EMNLP 2020 Quantifying the Contextualization of Word Representations with Semantic Class Probing EMNLP 2020 Analytical Methods for Interpretable Ultradense Word Embeddings IJCNLP 2019 Analytical Methods for Interpretable Ultradense Word Embeddings EMNLP 2019 Embedding Learning Through Multilingual Concept Induction ACL 2018