Skip to main content
    Skip to main contentSkip to navigationSkip to footer
    Artificial Intelligence
    (Koreferenzauflösung)

    Coreference Resolution

    Also known as:
    Coref Resolution
    Anaphora Resolution
    Pronoun Resolution
    Updated: 2/10/2026

    Identifying all mentions in text that refer to the same entity (e.g., "Angela Merkel" → "she" → "the chancellor").

    Quick Summary

    Coreference resolution identifies which text mentions refer to the same entity – essential for knowledge graphs and document understanding.

    Explanation

    Coreference resolution links pronouns, descriptions, and names into coherent entity clusters for deep text understanding.

    Marketing Relevance

    Essential for information extraction, summarization, and knowledge graph construction from long documents.

    Common Pitfalls

    Gender bias in pronoun resolution. Difficult in long texts. Cultural differences in reference patterns.

    Origin & History

    Hobbs' algorithm (1978) was an early rule-based system. Stanford Coref (2010) used statistical methods. Neural models (Lee et al., 2017) and SpanBERT (2020) now achieve >80% F1 on OntoNotes.

    Comparisons & Differences

    Coreference Resolution vs. Named Entity Recognition

    NER finds entities; coreference resolution links different mentions of the same entity.

    Coreference Resolution vs. Entity Linking

    Entity linking connects entities to knowledge base entries; coreference links mentions within a text.

    Related Services

    Related Terms

    👋Questions? Chat with us!