October 11, 2020 /

IMS presents 6 papers at COLING

The following papers by IMS researchers have been accepted at COLING. Congratulations to the authors!

  • Jan Hofmann, Enrica Troiano, Kai Sassenberg, and Roman Klinger: "Appraisal theories for emotion classification in text"
  • Enrica Troiano, Sebastian Padó, and Roman Klinger: "Lost in back-translation: Emotion preservation in neural machine translation."
  • Carina Silberer, Sina Zarrieß, Matthijs Westera and Gemma Boleda: "Humans Meet Models on Object Naming: A New Dataset and Analysis"
  • Talita Rani Anthonio and Michael Roth: "What Can We Learn from Noun Substitutions in Revision Histories?"
  • Tillmann Dönicke, Xiang Yu and Jonas Kuhn: "Real-Valued Logics for Typological Universals: Framework and Application"
  • Daniel Grießhaber, Johannes Maucher and Ngoc Thang Vu: "Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning"

Papers at co-located events

  • Henry Schäfer Felix Armbrust and Roman Klinger: "A computational analysis of financial and environmental narratives within financial reports and its value for investors." In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020), 2020.
  • Laura Oberländer and Roman Klinger: “Sequence labeling vs. clause classification for english emotion stimulus detection.” In Proceedings of the 9th Joint Conferene on Lexical and Computational Semantics, 2020
  • Melanie Andresen, Michael Vauth, and Heike Zinsmeister: "Modeling Ambiguity with Many Annotators and Self-Assessments of Annotator Certainty" In Proceedings of the 14th Linguistic Annotation Workshop, 2020
  • Laura Oberländer, Kevin Reich, and Roman Klinger: "Emotional people,stimuli, or targets: Which semantic roles enable machine learning toinfer emotions?" In Proceedings of the 3rd Workshop on Computational Modeling of People's Opinions, Personality, and Emotions in Social Media, Barcelona, Spain, December 2020. Association for Computational Linguistics
To the top of the page