DISCIE-Discriminative Closed Information Extraction

Authors: Cedric Möller, Ricardo Usbeck

Year: 2024

Conference: ISWC 2024

Abstract: This paper introduces a novel method for closed information extraction. The method employs a discriminative approach that incorporates type and entity-specific information to improve relation extraction accuracy, particularly benefiting long-tail relations. Notably, this method demonstrates superior performance compared to state-of-the-art end-to-end generative models. This is especially evident for the problem of large-scale closed information extraction where we are confronted with millions of entities and hundreds of relations. Furthermore, we emphasize the efficiency aspect by leveraging smaller models. In particular, the integration of type-information proves instrumental in achieving performance levels on par with or surpassing those of a larger generative model. This advancement holds promise for more accurate and efficient information extraction techniques.

Show BibTeX
@inproceedings{DBLP:conf/semweb/MollerU24,
  author       = {Cedric M{\"{o}}ller and
                  Ricardo Usbeck},
  editor       = {Gianluca Demartini and
                  Katja Hose and
                  Maribel Acosta and
                  Matteo Palmonari and
                  Gong Cheng and
                  Hala Skaf{-}Molli and
                  Nicolas Ferranti and
                  Daniel Hern{\'{a}}ndez and
                  Aidan Hogan},
  title        = {DISCIE-Discriminative Closed Information Extraction},
  booktitle    = {The Semantic Web - {ISWC} 2024 - 23rd International Semantic Web Conference,
                  Baltimore, MD, USA, November 11-15, 2024, Proceedings, Part {II}},
  series       = {Lecture Notes in Computer Science},
  volume       = {15232},
  pages        = {23--40},
  publisher    = {Springer},
  year         = {2024},
  url          = {https://doi.org/10.1007/978-3-031-77850-6\_2},
  doi          = {10.1007/978-3-031-77850-6\_2},
  timestamp    = {Sun, 02 Nov 2025 21:27:22 +0100},
  biburl       = {https://dblp.org/rec/conf/semweb/MollerU24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}