Knowledge Base Unification via Sense Embeddings and Disambiguation

@inproceedings{Bovi2015KnowledgeBU,
  title={Knowledge Base Unification via Sense Embeddings and Disambiguation},
  author={Claudio Delli Bovi and Luis Espinosa Anke and R. Navigli},
  booktitle={EMNLP},
  year={2015}
}
  • Claudio Delli Bovi, Luis Espinosa Anke, R. Navigli
  • Published in EMNLP 2015
  • Computer Science
  • We present KB-UNIFY, a novel approach for integrating the output of different Open Information Extraction systems into a single unified and fully disambiguated knowledge repository. KB-UNIFY consists of three main steps: (1) disambiguation of relation argument pairs via a sensebased vector representation and a large unified sense inventory; (2) ranking of semantic relations according to their degree of specificity; (3) cross-resource relation alignment and merging based on the semantic… CONTINUE READING
    On Aligning OpenIE Extractions with Knowledge Bases: A Case Study
    • 2020
    On the Limits of Aligning OpenIE Extractions with Knowledge Bases
    • 2020
    OPIEC: An Open Information Extraction Corpus
    7
    CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information
    33
    Merging knowledge bases in different languages
    4

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES
    Entity Linking meets Word Sense Disambiguation: a Unified Approach
    635
    A Probabilistic Approach for Integrating Heterogeneous Knowledge Sources
    25
    BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network
    1144
    Enriching Structured Knowledge with Open Information
    34
    Identifying Relations for Open Information Extraction
    1088
    YAGO3: A Knowledge Base from Multilingual Wikipedias
    385
    Open Information Extraction Using Wikipedia
    580
    SensEmbed: Learning Sense Embeddings for Word and Relational Similarity
    241