14 Papers accepted at EMNLP

We are happy to announce that 14 papers by members of our department have been accepted at the Empirical Methods in Natural Language Processing (EMNLP). Congratulations to all authors!

  • "We're Afraid Language Models Aren't Modeling Ambiguity." by Alisa Liu, Zhaofeng Wu, Julian Michael, Alane Suhr, Peter West, Alexander Koller, Swabha Swayamdipta, Noah A. Smith, Yejin Cho
    Long Paper
  • "SLOG: A Structural Generalization Benchmark for Semantic Parsing." by Bingzhi Li, Lucia Donatelli, Alexander Koller, Tal Linzen, Yuekun Yao, Najoung Kim.
    Long paper.
  • "Find-2-Find: Multitask Learning for Anaphora Resolution and Object Localization." by Cennet Oguz, Pascal Denis, Simon Ostermann, Emmanuel Vincent, Josef van Genabith.
    EMNLP 2023 long paper. DFKI/UdS/SFB 1102.
  • "Multilingual Coarse Political Stance Classification of Media. The Editorial Line of a ChatGPT and Bard Newspaper." by Cristina España Bonet.
    EMNLP 2023 Findings short paper. DFKI/UdS/SFB 1102.
  • "GPT-like Models are Bad Babies: A closer Look into the Relationship of Linguistic Competence and Psycholinguistic Measures"  by Julius Steuer, Marius Mosbach, Dietrich Klakow.
    EMNLP 2023 Workshop CoNLLCMCL Shared Task BabyLM
  • "Understanding and Mitigating Classification Errors Through Interpretable Token Patterns" by Michael Hedderich, Jonas Fischer, Dietrich Klakow, Jilles Vreeken.
    EMNLP Workshop BlackboxNLP.
  • "InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations." by Nils Feldhus, Qianli Wang, Tatiana Anikina, Sahil Chopra, Cennet Oguz, Sebastian Mölle
    EMNLP 2023 Findings long paper. DFKI/UdS/SFB 1102.
  • "Translating away Translationese without Parallel Data." by Rricha Jalotta, Koel Dutta Chowdhury, Cristina España Bonet, Josef van Genabith.
    EMNLP 2023 Long paper. DFKI/UdS/SFB 1102
  • "Where exactly does contextualization in a PLM happen?" by Soniya Vijayakumar, Simon Ostermann, Tanja Bäumel and Josef van Genabith.
    BlackBoxNLP WS @ EMNLP 2023 extended abstract. DFKI/UdS
  • "Investigating the Encoding of Words in BERT's Neurons using Feature Textualization." by Tanja Baeumel, Soniya Vijayakumar, Josef van Genabith, Guenter Neumann and Simon Ostermann.
    BlackBoxNLP WS @ EMNLP 2023 Long Paper DFKI/UdS.
  • "Multilingual coreference resolution: Adapt and Generate." by Tatiana Anikina, Natalia Skachkova and Anna Mokhova.
    The CRAC 2023 Workshop (the Sixth Workshop on Computational Models of Reference, Anaphora and Coreference) at EMNLP 2023
  • "A Lightweight Method to Generate Unanswerable Questions" by Vagrant Goutam, Miaoran Zhang, Dietrich Klakow.
    EMNLP Findings long.
  • "Do pre-trained language models and humans have similar behaviours in causal inference with script knowledge?" by Xudong Hong, Margarita Ryzhova, Daniel Adrian Biondi, Vera Demberg
    Findings long paper
  • "Shared Lexical Items as Triggers of Code Switching." by Shuly Wintner, Safaa Shehadi, Yuli Zeira, Doreen Osmelak and Yuval Nov