Nine papers authored or co-authored by UKP members have been accepted for publication at EMNLP 2021, the Conference on Empirical Methods in Natural Language Processing. The conference will be held online and in Punta Cana, Dominican Republic, November 7th – 11th, 2021.

The accepted papers are:

• What to Pre-Train on? Efficient Intermediate Task Selection
  Clifton Poth, Jonas Pfeiffer, Andreas Rücklé, and Iryna Gurevych
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts
  Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, and Sebastian Ruder
• Structural Adapters in Pretrained Language Models for AMR-to-text Generation
  Leonardo F. R. Ribeiro, Yue Zhang, and Iryna Gurevych
• AdapterDrop: On the Efficiency of Adapters in Transformers
  Andreas Rücklé, Gregor Geigle, Max Glockner, Tilman Beck, Jonas Pfeiffer, Nils Reimers, and Iryna Gurevych
• TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning
  Kexin Wang, Nils Reimers, and Iryna Gurevych
• Event Coreference Data (Almost) for Free: Mining Hyperlinks from Online News
  Michael Bugert and Iryna Gurevych
• Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation
  Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang, and Iryna Gurevych
• Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning
  Prasetya Utama, Nafise Sadat Moosavi, Victor Sanh, and Iryna Gurevych
• A Neural Graph-based Local Coherence Model
  Mohsen Mesgar, Leonardo F. R. Ribeiro, and Iryna Gurevych