All Stories

  1. Compressed Concatenation of Small Embedding Models
  2. WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval
  3. Teaching Computers to Understand Subtle Language Tricks Like Irony, Repetition, and Contrast
  4. Mixture of Modular Experts: Distilling Knowledge from a Multilingual Teacher into Specialized Modular Language Models
  5. MemBERT: Foundation model for memory forensics
  6. Impact of Position Bias on Language Models in Token Classification
  7. A Dataset of German Legal Reference Annotations
  8. Ontological representations of rhetorical figures for argument mining