Papers

    Research advancing document AI

    Academic work behind our models for information extraction, document understanding and structured generation.

    100+ citations across our published research
    Publications
    • 2024
      November 2024

      NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data

      Sergei Bogdanov, Alexandre Constantin, Timothée Bernard, Benoît Crabbé, Etienne Bernard
      EMNLP 2024 — Conference on Empirical Methods in Natural Language Processing

      Large Language Models have shown impressive abilities in data annotation, opening the way for new approaches to solve classic NLP problems. We show how to use LLMs to create NuNER, a compact language representation model specialized in Named Entity Recognition. NuNER can be fine-tuned to solve downstream NER problems in a data-efficient way, outperforming similarly-sized foundation models and competing with much larger LLMs.