Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models
ter Horst H, Hartung M, Cimiano P (2017)
In: Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference). Gracia J, Bond F, McCrae JP, Buitelaar P, Chiarcos C, Hellmann S (Eds); Lecture Notes in Artificial Intelligence, 10318. Springer: 166-180.
Sammelwerksbeitrag
| Veröffentlicht | Englisch
Download
preprint.pdf
579.63 KB
Herausgeber*in
Gracia, Jorge;
Bond, Francis;
McCrae, John P.;
Buitelaar, Paul;
Chiarcos, Christian;
Hellmann, Sebastian
Einrichtung
Abstract / Bemerkung
The problems of recognizing mentions of entities in texts and linking them to unique knowledge base identifiers have received considerable attention in recent years. In this paper we present a probabilistic system based on undirected graphical models that jointly addresses both the entity recognition and the linking task. Our framework considers the span of mentions of entities as well as the corresponding knowledge base identifier as random variables and models the joint assignment using a factorized distribution. We show that our approach can be easily applied to different technical domains by merely exchanging the underlying ontology. On the task of recognizing and linking disease names, we show that our approach outperforms the state-of-the-art systems DNorm and TaggerOne, as well as two strong lexicon-based baselines. On the task of recognizing and linking chemical names, our system achieves comparable performance to the state-of-the-art.
Stichworte
Joint entity recognition and linking;
Undirected probabilistic graphical models;
Diseases;
Chemicals
Erscheinungsjahr
2017
Buchtitel
Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference)
Serientitel
Lecture Notes in Artificial Intelligence
Band
10318
Seite(n)
166-180
Konferenz
1st International Conference on Language, Data, and Knowledge (LDK)
Konferenzort
Galway, Ireland
Konferenzdatum
2017-06-19 – 2017-06-20
Page URI
https://pub.uni-bielefeld.de/record/2910336
Zitieren
ter Horst H, Hartung M, Cimiano P. Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models. In: Gracia J, Bond F, McCrae JP, Buitelaar P, Chiarcos C, Hellmann S, eds. Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference). Lecture Notes in Artificial Intelligence. Vol 10318. Springer; 2017: 166-180.
ter Horst, H., Hartung, M., & Cimiano, P. (2017). Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models. In J. Gracia, F. Bond, J. P. McCrae, P. Buitelaar, C. Chiarcos, & S. Hellmann (Eds.), Lecture Notes in Artificial Intelligence: Vol. 10318. Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference) (pp. 166-180). Springer.
ter Horst, Hendrik, Hartung, Matthias, and Cimiano, Philipp. 2017. “Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models”. In Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference), ed. Jorge Gracia, Francis Bond, John P. McCrae, Paul Buitelaar, Christian Chiarcos, and Sebastian Hellmann, 10318:166-180. Lecture Notes in Artificial Intelligence. Springer.
ter Horst, H., Hartung, M., and Cimiano, P. (2017). “Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models” in Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference), Gracia, J., Bond, F., McCrae, J. P., Buitelaar, P., Chiarcos, C., and Hellmann, S. eds. Lecture Notes in Artificial Intelligence, vol. 10318, (Springer), 166-180.
ter Horst, H., Hartung, M., & Cimiano, P., 2017. Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models. In J. Gracia, et al., eds. Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference). Lecture Notes in Artificial Intelligence. no.10318 Springer, pp. 166-180.
H. ter Horst, M. Hartung, and P. Cimiano, “Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models”, Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference), J. Gracia, et al., eds., Lecture Notes in Artificial Intelligence, vol. 10318, Springer, 2017, pp.166-180.
ter Horst, H., Hartung, M., Cimiano, P.: Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models. In: Gracia, J., Bond, F., McCrae, J.P., Buitelaar, P., Chiarcos, C., and Hellmann, S. (eds.) Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference). Lecture Notes in Artificial Intelligence. 10318, p. 166-180. Springer (2017).
ter Horst, Hendrik, Hartung, Matthias, and Cimiano, Philipp. “Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models”. Language, Data, and Knowledge (Proceedings of the 1st International LDK Conference). Ed. Jorge Gracia, Francis Bond, John P. McCrae, Paul Buitelaar, Christian Chiarcos, and Sebastian Hellmann. Springer, 2017.Vol. 10318. Lecture Notes in Artificial Intelligence. 166-180.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Name
preprint.pdf
579.63 KB
Access Level
Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:47Z
MD5 Prüfsumme
8606c9bc63096b5ebdb65f582fd23f04
Google Scholar