Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-based Information Extraction

ter Horst H, Hartung M, Klinger R, Brazda N, Müller HW, Cimiano P (2018)
In: Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB). Silberztein M, Atigui F, Kornyshova E, Métais E, Meziane F (Eds); Lecture Notes in Computer Science, 10859. Cham: Springer International Publishing: 179-190.

Download
OA 442.44 KB
Sammelwerksbeitrag | Veröffentlicht | Englisch
Autor
; ; ; ; ;
Herausgeber
; ; ; ;
Abstract / Bemerkung
Template-based information extraction generalizes over standard token-level binary relation extraction in the sense that it attempts to fill a complex template comprising multiple slots on the basis of information given in a text. In the approach presented in this paper, templates and possible fillers are defined by a given ontology. The information extraction task consists in filling these slots within a template with previously recognized entities or literal values. We cast the task as a structure prediction problem and propose a joint probabilistic model based on factor graphs to account for the interdependence in slot assignments. Inference is implemented as a heuristic building on Markov chain Monte Carlo sampling. As our main contribution, we investigate the impact of soft constraints modeled as single slot factors which measure preferences of individual slots for ranges of fillers, as well as pairwise slot factors modeling the compatibility between fillers of two slots. Instead of relying on expert knowledge to acquire such soft constraints, in our approach they are directly captured in the model and learned from training data. We show that both types of factors are effective in improving information extraction on a real-world data set of full-text papers from the biomedical domain. Pairwise factors are shown to particularly improve the performance of our extraction model by up to +0.43 points in precision, leading to an F 1 score of 0.90 for individual templates.
Erscheinungsjahr
Buchtitel
Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB)
Band
10859
Seite
179-190
Konferenz
23rd International Conference on Natural Language & Information Systems (NLDB)
Konferenzort
Paris
Konferenzdatum
2018-06-13 – 2018-06-15
PUB-ID

Zitieren

ter Horst H, Hartung M, Klinger R, Brazda N, Müller HW, Cimiano P. Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-based Information Extraction. In: Silberztein M, Atigui F, Kornyshova E, Métais E, Meziane F, eds. Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB). Lecture Notes in Computer Science. Vol 10859. Cham: Springer International Publishing; 2018: 179-190.
ter Horst, H., Hartung, M., Klinger, R., Brazda, N., Müller, H. W., & Cimiano, P. (2018). Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-based Information Extraction. In M. Silberztein, F. Atigui, E. Kornyshova, E. Métais, & F. Meziane (Eds.), Lecture Notes in Computer Science: Vol. 10859. Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB) (pp. 179-190). Cham: Springer International Publishing. doi:10.1007/978-3-319-91947-8_18
ter Horst, H., Hartung, M., Klinger, R., Brazda, N., Müller, H. W., and Cimiano, P. (2018). “Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-based Information Extraction” in Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB), Silberztein, M., Atigui, F., Kornyshova, E., Métais, E., and Meziane, F. eds. Lecture Notes in Computer Science, vol. 10859, (Cham: Springer International Publishing), 179-190.
ter Horst, H., et al., 2018. Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-based Information Extraction. In M. Silberztein, et al., eds. Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB). Lecture Notes in Computer Science. no.10859 Cham: Springer International Publishing, pp. 179-190.
H. ter Horst, et al., “Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-based Information Extraction”, Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB), M. Silberztein, et al., eds., Lecture Notes in Computer Science, vol. 10859, Cham: Springer International Publishing, 2018, pp.179-190.
ter Horst, H., Hartung, M., Klinger, R., Brazda, N., Müller, H.W., Cimiano, P.: Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-based Information Extraction. In: Silberztein, M., Atigui, F., Kornyshova, E., Métais, E., and Meziane, F. (eds.) Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB). Lecture Notes in Computer Science. 10859, p. 179-190. Springer International Publishing, Cham (2018).
ter Horst, Hendrik, Hartung, Matthias, Klinger, Roman, Brazda, Nicole, Müller, Hans Werner, and Cimiano, Philipp. “Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-based Information Extraction”. Proceedings of the 23rd International Conference on Natural Language & Information Systems (NLDB). Ed. Max Silberztein, Faten Atigui, Elena Kornyshova, Elisabeth Métais, and Farid Meziane. Cham: Springer International Publishing, 2018.Vol. 10859. Lecture Notes in Computer Science. 179-190.
Volltext(e)
Name
442.44 KB
Access Level
OA Open Access
Zuletzt Hochgeladen
2018-04-10T15:23:23Z

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche