nach oben

Erschienen in:

2012 | Buchkapitel

5. Entity Linking: Finding Extracted Entities in a Knowledge Base

verfasst von : Delip Rao, Paul McNamee, Mark Dredze

Verlag: Springer Berlin Heidelberg

Einloggen, um Zugang zu erhalten

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

In the menagerie of tasks for information extraction, entity linking is a new beast that has drawn a lot of attention from NLP practitioners and researchers recently. Entity Linking, also referred to as record linkage or entity resolution, involves aligning a textual mention of a named-entity to an appropriate entry in a knowledge base, which may or may not contain the entity. This has manifold applications ranging from linking patient health records to maintaining personal credit files, prevention of identity crimes, and supporting law enforcement. We discuss the key challenges present in this task and we present a high-performing system that links entities using max-margin ranking. We also summarize recent work in this area and describe several open research problems.

http://www.clsp.jhu.edu/~markus/fstrain

www.cs.cornell.edu/people/tj/svm_light/svm_rank.html

Bunescu and Pasca [13] report learning tens of thousands of support vectors with their “taxonomy” kernel while a linear kernel represents all support vectors with a single weight vector, enabling faster training and prediction.

We used multiple lists, including class-specific lists (i.e., for PER, ORG, and GPE) lists extracted from Freebase [41] and Wikipedia redirects. PER, ORG, and GPE are the commonly used terms for entity types for people, organizations and geo-political regions respectively.

Without such a limit, the objective function may diverge for certain parameters of the model; we detect such cases and learn to avoid them during training.

Data available from www.dredze.com

http://en.wikipedia.org/wiki/Help:Infobox

http://research.microsoft.com/en-us/um/people/silviu/WebAssistant/TestData/

One of the MSNBC news articles is no longer available so we used 759 total entities.

We removed Google, FST and conjunction features which reduced system accuracy but increased performance.

vs. 2006 version used in [14] We could not get the 2006 version from the author or the Internet.

Since our KB was derived from infoboxes, entities not having an infobox were left out.

As this article went to press we became aware of the efforts by Mayfield et al. [49] to construct a cross-language entity linking test collection where the language of the knowledge base is English, but query names are in many languages.

Sang, E.T.K., Meulder, F.D.: Introduction to the conll-2003 shared task: language-independent named entity recognition. In: Conference on Natural Language Learning (CONLL), Edmonton. The Association for Computational Linguistics, Stroudsburg (2003)

Asahara, M., Matsumoto, Y.: Japanese named entity extraction with redundant morphological analysis. In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - vol. 1, NAACL ’03, Stroudsburg, pp. 8–15. Association for Computational Linguistics, Stroudsburg (2003)

McCallum, A., Li, W.: Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons. In: Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - vol. 4, CONLL ’03, Stroudsburg, pp. 188–191. Association for Computational Linguistics, Stroudsburg (2003)

Collins, M., Singer, Y.: Unsupervised models for named entity classification. In: In Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, College Park, pp. 100–110. Association for Computational Linguistics, New Brunswick (1999)

Cucerzan, S., Yarowsky, D.: Language independent ner using a unified model of internal and contextual evidence. In: Proceedings of the 6th Conference on Natural Language Learning - vol. 20, COLING-02, Stroudsburg, pp. 1–4. Association for Computational Linguistics, Stroudsburg (2002)

Nadeau, D., Sekine, S.: A survey of named entity recognition and classification. Linguisticae Investigationes, vol. 30, pp. 3–26. John Benjamins, Amsterdam (2007)

Bagga, A., Baldwin, B.: Entity-based cross-document coreferencing using the vector space model. In: Conference on Computational Linguistics (COLING), Montreal. Association for Computational Linguistics, Stroudsburg (1998)

van Deemter, K., Kibble, R.: On coreferring: coreference in muc and related annotation schemes. Comput. Linguist. 26, 629–637 (2000)

Yang, X., Zhou, G., Su, J., Tan, C.L.: Coreference resolution using competition learning approach. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, Sapporo, pp. 176–183 (2003)

10.

Ng, V.: Supervised noun phrase coreference research: The first fifteen years. In: Proceedings of the ACL, Uppsala, pp. 1396–1411. Association for Computational Linguistics, Stroudsburg (2010)

11.

Banko, M., Etzioni, O.: The tradeoffs between open and traditional relation extraction. In: Association for Computational Linguistics, Columbus (2008)

12.

Sutton, C., Mccallum, A.: Introduction to conditional random fields for relational learning. In: Getoor, L., Taskar, B., (eds.) Introduction to Statistical Relational Learning. MIT, Cambridge (2006)

13.

Bunescu, R.C., Pasca, M.: Using encyclopedic knowledge for named entity disambiguation. In: European Chapter of the Assocation for Computational Linguistics (EACL), Trento (2006)

14.

Cucerzan, S.: Large-scale named entity disambiguation based on wikipedia data. In: Empirical Methods in Natural Language Processing (EMNLP), Prague. Association for Computational Linguistics, Stroudsburg (2007)

15.

Mann, G.S., Yarowsky, D.: Unsupervised personal name disambiguation. In: Conference on Natural Language Learning (CONLL), Edmonton. Johns Hopkins University, Baltimore (2003)

16.

Artiles, J., Sekine, S., Gonzalo, J.: Web people search: results of the first evaluation and the plan for the second. In: WWW, Beijing. ACM, New York (2008)

17.

Poesio, M., Day, D., Artstein, R., Duncan, J., Eidelman, V., Giuliano, C., Hall, R., Hitzeman, J., Jern, A., Kabadjov, M., Yong, S., Keong, W., Mann, G., Moschitti, A., Ponzetto, S., Smith, J., Steinberger, J., Strube, M., Su, J., Versley, Y., Yang, X., Wick, M.: Exploiting lexical and encyclopedic resources for entity disambiguation: final report. Technical Report, JHU CLSP 2007 Summer Workshop, Johns Hopkins University, Baltimore (2008)

18.

Popescu, O.: Dynamic parameters for cross document coreference. In: Conference on Computational Linguistics (COLING), Beijing (2010)

19.

Huang, J., Treeratpituk, P., Taylor, S., Giles, C.L.: Enhancing cross document coreference of web documents with context similarity and very large scale text categorization. In: Conference on Computational Linguistics (COLING), Beijing. Association for Computational Linguistics, Stroudsburg (2010)

20.

Singh, S., Subramanya, A., Pereira, F., McCallum, A.: Large-scale cross-document coreference using distributed inference and hierarchical models. In: Association for Computational Linguistics, Portland. Association for Computational Linguistics, Stroudsburg (2011)

21.

Rao, D., McNamee, P., Dredze, M.: Streaming cross document entity coreference resolution. In: Conference on Computational Linguistics (COLING), Beijing. Association for Computational Linguistics, Stroudsburg (2010)

22.

Ng, V.: Supervised noun phrase coreference research: The first fifteen years. In: Association for Computational Linguistics, Uppsala. Association for Computational Linguistics, Stroudsburg (2010)

23.

Raghunathan, K., Lee, H., Rangarajan, S., Chambers, N., Surdeanu, M., Jurafsky, D., Manning, C.: A multi-pass sieve for coreference resolution. In: Empirical Methods in Natural Language Processing (EMNLP), Massachusetts. Association for Computational Linguistics, Stroudsburg (2010)

24.

Elsner, M., Charniak, E.: The same-head heuristic for coreference. In: Association for Computational Linguistics, Uppsala. Association for Computational Linguistics, Stroudsburg (2010)

25.

Stoyanov, V., Cardie, C., Gilbert, N., Riloff, E., Buttler, D., Hysom, D.: Reconcile: A coreference resolution research platform. In: Association for Computational Linguistics, Uppsala (2010)

26.

Gabbard, R., Freedman, M., Weischedel, R.: Coreference for learning to extract relations: Yes virginia, coreference matters. In: Association for Computational Linguistics, Portland. Association for Computational Linguistics, Stroudsburg (2011)

27.

McNamee, P., Dang, H.T.: Overview of the TAC 2009 knowledge base population track. In: Text Analysis Conference (TAC), Gaithersburg (2009)

28.

Ji, H., Grishman, R.: Knowledge base population: successful approaches and challenges. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL-HLT), Portland. Association for Computational Linguistics, Stroudsburg (2011)

29.

Zhang, W., Su, J., Tan, C.L.: Entity linking leveraging automatically generated annotation. In: Conference on Computational Linguistics (COLING), Beijing (2010)

30.

Gottipati, S., Jiang, J.: Linking entities to a knowledge base with query expansion. In: Empirical Methods in Natural Language Processing (EMNLP), Edinburgh. Association for Computational Linguistics, Stroudsburg (2011)

31.

Han, X., Sun, L.: A generative entity-mention model for linking entities with knowledge base. In: Association for Computational Linguistics, Portland. Association for Computational Linguistics, Stroudsburg (2011)

32.

Lehmann, J., Monahan, S., Nezda, L., Jung, A., Shi, Y.: Lcc approaches to knowledge base population at tac 2010. In: Proceeding TAC 2010 Workshop, National Institute of Standards and Technology, Gaithersburg (2010)

33.

Zhang, W., Sim, Y., Su, J., Tan, C.: Nus-i2r: Learning a combined system for entity linking. In: Proceeding TAC 2010 Workshop, National Institute of Standards and Technology, Gaithersburg (2010)

34.

Zhang, W., Sim, Y.C., Su, J., Tan, C.L.: Entity linking with effective acronym expansion instance selection and topic modeling. In: International Joint Conference on Artificial Intelligence, Barcelona (2011)

35.

Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE Trans. Knowl. Data Eng. 19, 1–16 (2007)

36.

McCallum, A., Nigam, K., Ungar, L.: Efficient clustering of high-dimensional data sets with application to reference matching. In: Knowledge Discovery and Data Mining (KDD), Boston. ACM, New York (2000)

37.

Joachims, T.: Optimizing search engines using clickthrough data. In: Knowledge Discovery and Data Mining (KDD), Edmonton. ACM, New York (2002)

38.

McNamee, P., Dredze, M., Gerber, A., Garera, N., Finin, T., Mayfield, J., Piatko, C., Rao, D., Yarowsky, D., Dreyer, M.: HLTCOE approaches to knowledge base population at TAC 2009. In: Text Analysis Conference (TAC), Gaithersburg (2009)

39.

Christen, P.: A comparison of personal name matching: techniques and practical issues. Technical Report TR-CS-06-02, Australian National University, Australia (2006)

40.

Dreyer, M., Smith, J., Eisner, J.: Latent-variable modeling of string transductions with finite-state methods. In: Empirical Methods in Natural Language Processing (EMNLP), Honolulu. Association for Computational Linguistics, Stroudsburg (2008)

41.

Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: SIGMOD Management of Data, Vancouver. ACM, New York (2008)

42.

Syed, Z., Finin, T., Joshi, A.: Wikipedia as an ontology for describing documents. In: Proceedings of the Second International Conference on Weblogs and Social Media, Chicago. AAAI, Menlo Park (2008)

43.

Fader, A., Soderland, S., Etzioni, O.: Scaling Wikipedia-based named entity disambiguation to arbitrary web text. In: WikiAI09 Workshop at IJCAI 2009, Pasadena (2009)

44.

Boschee, E., Weischedel, R., Zamanian, A.: Automatic information extraction. In: Conference on Intelligence Analysis, Washington (2005)

45.

Salton, G., McGill, M.: Introduction to Modern Information Retrieval. McGraw-Hill, New York (1983)

46.

Klein, M., Nelson, M.L.: A comparison of techniques for estimating IDF values to generate lexical signatures for the web. In: Workshop on Web Information and Data Management (WIDM), Napa Valley. ACM, New York (2008)

47.

Simpson, H., Parker, R., Strassel, S., Dang, H.T., McNamee, P.: Wikipedia and the web of confusable entities: experience from entity profile creation for tac knowledge base population. In: Proceedings of the Seventh International Language Resources and Evaluation Conference (LREC), Valletta. European Language Resources Association, Valletta (2010)

48.

Li, F., Zhang, Z., Bu, F., Tang, Y., Zhu, X., Huang, M.: THU QUANTA at TAC 2009 KBP and RTE track. In: Text Analysis Conference (TAC), National Institute of Standards and Technology, Gaithersburg (2009)

49.

Mayfield, J., Lawrie, D., McNamee, P., Oard, D.W.: Building a cross-language entity linking collection in twenty-one languages. In: Proceedings of the Cross Language Evaluate Forum (CLEF), Amsterdam (2011)

Titel: Entity Linking: Finding Extracted Entities in a Knowledge Base
verfasst von: Delip Rao
Paul McNamee
Mark Dredze
Verlag: Springer Berlin Heidelberg
DOI: https://doi.org/10.1007/978-3-642-28569-1_5

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.