Elamur Research⌕
☰
home / papers / 2016 / Revisiting Taxonomy Induction over Wikipedia

Revisiting Taxonomy Induction over Wikipedia

Paper · 2016 · Amit Gupta, Francesco Piccinno, Mikhail Kozhevnikov et al.

Summary

The paper addresses a long-standing difficulty in deriving a clean taxonomy from the Wikipedia category network (WCN). Many links from pages to categories, and from categories to their parents, do not express is-a relations. Even when individual links are mostly correct, chains of upward links tend to accumulate errors. As a result, entities end up attached to absurd distant ancestors. The authors build HEADS, a single taxonomy covering both pages and categories. It is produced by an ordered cascade of linguistically motivated heuristics that rely mainly on the lexical heads of category titles. These are combined with corpus-wide head statistics, type similarity between heads, and defining lemmas from the first sentences of articles. A pruning stage then removes categories that add only temporal, locational or attribute-grouping information. The authors also propose an evaluation framework that judges whole generalization paths rather than single edges. Against the state of the art (WiBi), HEADS yields generalizations that are more than twice as accurate, with comparable coverage. This matters because downstream applications depend on reliable long-range generalizations.

Key points

  • Prior systems compared include WikiTaxonomy, WikiNet, YAGO, DBPedia and WiBi. WiBi reaches roughly 85% edge-level accuracy but does not use the syntax of category titles.
  • Category heuristics include Same head, Global head support, Type similarity, Only plural/singular parent, Grouping child/parent category (titles of the form "X by Y"), Suffix head, Lookahead candidates and Title head.
  • Page heuristics include Exact defining lemma, Type-similar lemma, Plural head and Transfer.
  • The heuristics are ordered from most to least precise, with precision determined on a hand-labeled development set. For each node, the cascade stops at the first heuristic that proposes a candidate. Maintenance categories (e.g. "stubs", "articles") are filtered out beforehand.
  • An extrinsic test generalizes slot fillers of templates mined from page titles (e.g. "Passport of [X]", "Tomb of [X]"). In this test, HEADS picks compact, meaningful classes, while the WiBi variants return noisy ones. The taxonomy is released at headstaxonomy.com.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢GoogleMountain View · United States533 works · 443,884 citations🎓Saarland UniversitySaarbrücken · Germany153 works · 18,502 citations🎓University of PisaPisa · Italy27 works · 4,102 citations🎓Indian Institute of Science BangaloreBengaluru · India16 works · 1,462 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 19,503 worksArtificial Intelligence · 18,805 worksArts and Humanities · 17,959 worksLanguage and Linguistics · 17,789 works

Cite

Cite as Amit Gupta, Francesco Piccinno, Mikhail Kozhevnikov, Marius Paşca and Daniele Pighin. 2016. Revisiting Taxonomy Induction over Wikipedia. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers.

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{gupta2016revisiting,
  title = {{Revisiting Taxonomy Induction over Wikipedia}},
  author = {Amit Gupta, Francesco Piccinno, Mikhail Kozhevnikov, Marius Paşca and Daniele Pighin},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  year = {2016},
  url = {https://aclanthology.org/C16-1217/}
}

References

21 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. G. de Melo and G. Weikum. 2010. MENTA: Inducing multilingual taxonomies from Wikipedia. In Proceedings of the 19th International Conference on Information and Knowledge Management, pages 1099–1108. find
  2. X. Dong, E. Gabrilovich, G. Heitz, W. Horn, N. Lao, and K. Murphy. 2014. Knowledge Vault: A Web-scale approach to probabilistic knowledge fusion. In Proceedings of the 20th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 601–610, New York, NY. find
  3. David Ferrucci, Eric Brown, Jennifer Chu-Carroll, James Fan, David Gondek, Aditya A Kalyanpur, Adam Lally, J William Murdock, Eric Nyberg, John Prager, et al. 2010. Building Watson: An overview of the DeepQA project. AI Magazine, 31(3):59–79. find
  4. T. Flati, D. Vannella, T. Pasini, and R. Navigli. 2014. Two is bigger (and better) than one: the Wikipedia Bitaxonomy project. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 945–955, Baltimore, Maryland. Association for Computational Linguistics. find
  5. M. Hearst. 1992. Automatic acquisition of hyponyms from large text corpora. In Proceedings of the 14th Conference on Computational Linguistics, pages 539–545, Nantes, France.
  6. J. Hoffart, F. Suchanek, K. Berberich, and G. Weikum. 2013. YAGO2: a spatially and temporally enhanced knowledge base from Wikipedia. Artificial Intelligence Journal. Special Issue on Artificial Intelligence, Wikipedia and Semi-Structured Resources, 194:28–61. find
  7. E. Hovy, R. Navigli, and S. Ponzetto. 2013. Collaboratively built semi-structured content and Artificial Intelligence: The story so far. Artificial Intelligence, 194:2–27. find
  8. J. Hu, G. Wang, F. Lochovsky, J. Sun, and Z. Chen. 2009. Understanding user’s query intent with Wikipedia. In Proceedings of the 18th World Wide Web Conference, pages 471–480, Madrid, Spain. find
  9. J. Lehmann, R. Isele, M. Jakob, A. Jentzsch, D. Kontokostas, P. Mendes, S. Hellmann, M. Morsey, P. van Kleef, and S. Auer et al. 2015. DBpedia–a large-scale, multilingual knowledge base extracted from Wikipedia. Semantic Web, 6(2):167–195.
  10. R. Mihalcea. 2007. Using Wikipedia for automatic word sense disambiguation. In Proceedings of the 2007 Conference of the North American Association for Computational Linguistics, pages 196–203, Rochester, New York. find
  11. V. Nastase and M. Strube. 2008. Decoding Wikipedia categories for knowledge acquisition. In AAAI, volume 8, pages 1219–1224. find
  12. V. Nastase and M. Strube. 2013. Transforming Wikipedia into a large scale multilingual concept network. Artificial Intelligence, 194:62–85. find
  13. V. Nastase, M. Strube, B. Börschinger, C. Zirn, and A. Elghafari. 2010. WikiNet: A very large scale multi-lingual concept network. In Proceedings of the 7th International Conference on Language Resources and Evaluation, pages 17–23, La Valetta, Malta. find
  14. S. Ponzetto and M. Strube. 2007. Deriving a large scale taxonomy from Wikipedia. In Proceedings of the 22nd National Conference on Artificial Intelligence, pages 1440–1445, Vancouver, British Columbia. find
  15. S. Ponzetto and M. Strube. 2011. Taxonomy induction based on a collaboratively built knowledge repository. Artificial Intelligence, 175(9–10):1737–1756. find
  16. L. Ratinov and D. Roth. 2012. Learning-based multi-sieve co-reference resolution with knowledge. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1234–1244, Jeju Island, Korea.
  17. L. Ratinov, D. Roth, D. Downey, and M. Anderson. 2011. Local and global algorithms for disambiguation to Wikipedia. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, pages 1375–1384, Portland, Oregon. find
  18. M. Remy. 2002. Wikipedia: The free encyclopedia. Online Information Review, 26(6):434. find
  19. F. Suchanek, G. Kasneci, and G. Weikum. 2007. Yago: A core of semantic knowledge unifying Wordnet and Wikipedia. In Proceedings of the 16th International World Wide Web Conference, pages 697–706, Banff, Canada. find
  20. D. Vrandec̆ić and M. Krötzsch. 2014. Wikidata: A free collaborative knowledge base. Communications of the ACM, 57:78–85. find
  21. F. Wu and D. Weld. 2010. Open information extraction using Wikipedia. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 118–127, Uppsala, Sweden.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/gupta-2016-revisiting-taxonomy-induction-over-wikipedia/