Elamur Research⌕
☰
home / papers / 2016 / J-NERD: Joint Named Entity Recognition and Disambiguation with Rich Linguistic Features

J-NERD: Joint Named Entity Recognition and Disambiguation with Rich Linguistic Features

Paper · 2016 · Dat Ba Nguyen, Martin Theobald and Gerhard Weikum

Summary

Typical entity-linking pipelines first detect and type name mentions (NER), then link them to a knowledge base (NED). Errors therefore cascade: spurious mentions lower linking precision, missed mentions cap recall, and knowledge about linked entities never reaches the recognizer. J-NERD solves both tasks in one step. It is a supervised, CRF-style factor graph. Its per-sentence structure follows the dependency parse tree instead of a flat word chain, and these sentence models are joined into a document-level model that favors coherent entity choices. Each token label pairs a coarse type (PER, ORG, LOC, MISC) with a candidate KB entity. Inference by Viterbi (exact) or Gibbs sampling (approximate) keeps competing spans and entity candidates open until a single joint decision is made. Features combine standard lexical cues, topical domain signals, and syntactic patterns, such as verbs linked to a mention through nsubj or dobj relations. On CoNLL'03, ACE'05 and ClueWeb'09-FACC1, J-NERD outperforms AIDA-light, TagMe, Spotlight and the Berkeley-entity joint system in end-to-end F1. This shows that coupling recognition and linking is worthwhile.

Key points

  • On ACE'05, J-NERD reaches 65.5 end-to-end F1. Berkeley-entity (Durrett and Klein, 2014) scores 63.7, the pipeline variant P-NERD 64.2, AIDA-light 62.8, TagMe 50.7 and Spotlight 41.4.
  • On ClueWeb, J-NERD gets 73.8 F1, ahead of AIDA-light (72.6), TagMe (68.3) and Spotlight (66.5). On the long-tail ClueWeb subset it scores 72.3.
  • For NER alone on CoNLL-YAGO2, J-NERD is roughly on par with dedicated taggers. Its typing F1 is 86.9, against 86.8 for Stanford NER and 85.3 for the Illinois Tagger. For boundary detection it scores 93.1, slightly below Stanford's 93.4.
  • In the ablation of the global tree model, end-to-end NERD F1 climbs from 74.3 with standard features to 78.7 with all features. Linguistic features (dependency-based, e.g. prep_for[play, England]) contribute more than domain features.
  • The source code is released by MPI for Informatics (jnerd-tacl.zip).

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

🔬Max Planck Institute for InformaticsSaarbrücken · Germany16 works · 4,453 citations🎓Universität UlmUlm · Germany4 works · 89 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksBiochemistry, Genetics and Molecular Biology · 234 worksMolecular Biology · 231 works

🧭 Topics 1Research subjects and languages the work is about.Named entity recognition · 200 works

Cite

Cite as Dat Ba Nguyen, Martin Theobald and Gerhard Weikum. 2016. J-NERD: Joint Named Entity Recognition and Disambiguation with Rich Linguistic Features. Transactions of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl_a_00094

@article{nguyen2016j,
  title = {{J-NERD: Joint Named Entity Recognition and Disambiguation with Rich Linguistic Features}},
  author = {Dat Ba Nguyen, Martin Theobald and Gerhard Weikum},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2016},
  doi = {10.1162/tacl\_a\_00094},
  url = {https://doi.org/10.1162/tacl_a_00094}
}

References

39 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. The results for ClueWeb are shown in Table 7. Again, J-NERD outperforms all other systems with a t-test p-value of 0.05. The differences between Luisa Bentivogli, Pamela Forner, Bernardo Magnini, and Emanuele Pianta. 2004. Revising the Wordnet Domains Hierarchy: Semantics, Coverage and Balancing. find
  2. In Proceedings of the Workshop on Multilingual Linguistic Ressources, MLR ’04, pages 101–108. ACL. Luisa Bentivogli, Pamela Forner, Claudio Giuliano, Alessandro Marchetti, Emanuele Pianta, and Kateryna Tymoshenko. 2010. find
  3. Extending English ACE 2005 Corpus Annotation with Ground-truth Links to Wikipedia. In The People’s Web Meets NLP: Collaboratively Constructed Semantic Resources ’10, pages 19–27. find
  4. COLING. Razvan Bunescu and Marius Pasca. 2006. Using Encyclopedic Knowledge for Named Entity Disambiguation. In EACL ’06, pages 9–16.
  5. ACL. David Carmel, Ming-Wei Chang, Evgeniy Gabrilovich, Bo-June Paul Hsu, and Kuansan Wang. 2014. ERD’14: Entity Recognition and Disambiguation Challenge. In SIGIR ’14, page 1292. find
  6. ACM. Marco Cornolti, Paolo Ferragina, and Massimiliano Ciaramita. 2013. A Framework for Benchmarking Entity-annotation Systems. In WWW ’13, pages 249– 260. ACM. Marco Cornolti, Paolo Ferragina, Massimiliano Ciaramita, Hinrich Schütze, and Stefan Rüd. 2014. The SMAPH System for Query Entity Recogni… find
  7. ACM. Silviu Cucerzan. 2007. Large-Scale Named Entity Disambiguation Based on Wikipedia Data. In EMNLP-CONLL ’07, pages 708–716. find
  8. ACL. Silviu Cucerzan. 2014. Name Entities Made Obvious: The Participation in the ERD 2014 Evaluation. In Proceedings of the First International Workshop on Entity Recognition and Disambiguation, ERD ’14, pages 95– 100. find
  9. ACM. Hamish Cunningham, Diana Maynard, Kalina Bontcheva, Valentin Tablan, Niraj Aswani, Ian Roberts, Genevieve Gorrell, Adam Funk, Angus Roberts, Danica Damljanovic, Thomas Heitz, Mark A. Greenwood, Horacio Saggion, Johann Petrak, Yaoyong Li, and Wim Peters. 2011. Text Processing with GATE. Universi… find
  10. Joachim Daiber, Max Jakob, Chris Hokamp, and Pablo N. Mendes. 2013. Improving Efficiency and Accuracy in Multilingual Entity Extraction. In Proceedings of the 9th International Conference on Semantic Systems, I-SEMANTICS ’13, pages 121–124. find
  11. ACM. Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. 2006. Generating typed dependency parses from phrase structure parses. In Proceedings of the International Conference on Language Resources and Evaluation, LREC ’06, pages 449–454. ELRA.
  12. Stephen Dill, Nadav Eiron, David Gibson, Daniel Gruhl, R. Guha, Anant Jhingran, Tapas Kanungo, Sridhar Rajagopalan, Andrew Tomkins, John A. Tomlin, and Jason Y. Zien. 2003. SemTag and Seeker: Bootstrapping the Semantic Web via Automated Semantic Annotation. In WWW ’03, pages 178–186. find
  13. ACM. Greg Durrett and Dan Klein. 2014. A Joint Model for Entity Analysis: Coreference, Typing, and Linking. In TACL ’14.
  14. ACL. Paolo Ferragina and Ugo Scaiella. 2010. TAGME: On-the-fly Annotation of Short Text Fragments (by Wikipedia Entities). In CIKM ’10, pages 1625–1628.
  15. ACM. Jenny Rose Finkel, Trond Grenager, and Christopher Manning. 2005. Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling. In ACL ’05, pages 363–370.
  16. ACL. Michael Fleischman and Eduard Hovy. 2002. Fine Grained Classification of Named Entities. In COLING ’02, pages 1–7. ACL. Johannes Hoffart, Mohamed Amir Yosef, Ilaria Bordino, Hagen Fürstenau, Manfred Pinkal, Marc Spaniol, Bilyana Taneva, Stefan Thater, and Gerhard Weikum. 2011. Robust Disambigu… find
  17. ACL. Johannes Hoffart, Stephan Seufert, Dat Ba Nguyen, Martin Theobald, and Gerhard Weikum. 2012. KORE: Keyphrase Overlap Relatedness for Entity Disambiguation. In CIKM ’12, pages 545–554. find
  18. ACM. Johannes Hoffart, Fabian M. Suchanek, Klaus Berberich, and Gerhard Weikum. 2013. YAGO2: A Spatially and Temporally Enhanced Knowledge Base from Wikipedia. Artificial Intelligence, 194:28–61. find
  19. Daphne Koller, Nir Friedman, Lise Getoor, and Benjamin Taskar. 2007. Graphical Models in a Nutshell. In An Introduction to Statistical Relational Learning. find
  20. MIT Press. Sayali Kulkarni, Amit Singh, Ganesh Ramakrishnan, and Soumen Chakrabarti. 2009. Collective Annotation of Wikipedia Entities in Web Text. In KDD ’09, pages 457–466. find
  21. ACM. Xiao Ling and Daniel S. Weld. 2012. Fine-grained Entity Recognition. In AAAI ’12. find
  22. AAAI Press. Dong C. Liu and Jorge Nocedal. 1989. On the Limited Memory BFGS Method for Large Scale Optimization. Mathematical Programming, 45(3):503–528. find
  23. Bernardo Magnini and Gabriela Cavagli. 2000. Integrating Subject Field Codes into Wordnet. In Proceedings of the International Conference on Language Resources and Evaluation, LREC ’00, pages 1413–1418.
  24. ELRA. Andrew McCallum and Wei Li. 2003. Early Results for Named Entity Recognition with Conditional Random Fields, Feature Induction and Web-enhanced Lexicons. In HLT-NAACL ’03, pages 188–191.
  25. ACL. Edgar Meij, Wouter Weerkamp, and Maarten de Rijke. 2012. Adding Semantics to Microblog Posts. In WSDM ’12, pages 563–572. ACM. Pablo N. Mendes, Max Jakob, Andrés Garcı́a-Silva, and Christian Bizer. 2011. Dbpedia Spotlight: Shedding Light on the Web of Documents. In Proceedings of the 7th Inter… find
  26. ACM. George A. Miller. 1995. WordNet: A Lexical Database for English. Communications of the ACM, 38(11):39– 41.
  27. David Milne and Ian H. Witten. 2008. Learning to Link with Wikipedia. In CIKM ’08, pages 509–518. find
  28. ACM. David Milne and Ian H. Witten. 2013. An Open-source Toolkit for Mining Wikipedia. Artificial Intelligence, 194:222–239. find
  29. Ndapandula Nakashole, Tomasz Tylenda, and Gerhard Weikum. 2013. Fine-grained Semantic Typing of Emerging Entities. In ACL ’13, pages 1488–1497. find
  30. ACL. Dat Ba Nguyen, Johannes Hoffart, Martin Theobald, and Gerhard Weikum. 2014. AIDA-light: High-Throughput Named-Entity Disambiguation. In Proceedings of the Workshop on Linked Data on the Web, LDOW ’14. find
  31. CEUR-WS.org. Alexandre Passos, Vineet Kumar, and Andrew McCallum. 2014. Lexicon Infused Phrase Embeddings for Named Entity Resolution. In CONLL ’14, pages 78– 86.
  32. ACL. Altaf Rahman and Vincent Ng. 2010. Inducing Fine-grained Semantic Classes via Hierarchical and Collective Classification. In COLING ’10, pages 931–939. find
  33. ACL. Lev Ratinov and Dan Roth. 2009. Design Challenges and Misconceptions in Named Entity Recognition. In CONLL ’09, pages 147–155.
  34. ACL. Lev Ratinov, Dan Roth, Doug Downey, and Mike Anderson. 2011. Local and Global Algorithms for Disambiguation to Wikipedia. In HLT ’11, pages 1375– 1384. find
  35. ACL. Avirup Sil and Alexander Yates. 2013. Re-ranking for Joint Named-Entity Recognition and Linking. In CIKM ’13, pages 2369–2374. find
  36. ACM. Valentin I. Spitkovsky and Angel X. Chang. 2012. A Cross-Lingual Dictionary for English Wikipedia Concepts. In Proceedings of the International Conference on Language Resources and Evaluation, LREC ’12. find
  37. ELRA. Charles A. Sutton and Andrew McCallum. 2012. An Introduction to Conditional Random Fields. Foundations and Trends in Machine Learning, 4(4):267–373. find
  38. Ricardo Usbeck, Michael Röder, Axel-Cyrille Ngonga Ngomo, Ciro Baron, Andreas Both, Martin Brümmer, Diego Ceccarelli, Marco Cornolti, Didier Cherix, Bernd Eickmann, Paolo Ferragina, Christiane Lemke, Andrea Moro, Roberto Navigli, Francesco Piccinno, Giuseppe Rizzo, Harald Sack, René Speck, Raphae… find
  39. ACM. Mohamed Amir Yosef, Sandro Bauer, Johannes Hoffart, Marc Spaniol, and Gerhard Weikum. 2012. HYENA: Hierarchical Type Classification for Entity Names. In COLING ’12, pages 1361–1370. ACL. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/nguyen-2016-j-nerd-joint-named-entity/