Automatic knowledge-graph creation from historical documents: The Chilean dictatorship as a case study

Simple item page
dc.catalogadoryvc
dc.contributor.authorDíaz, Camila
dc.contributor.authorDunstan Escudero, Jocelyn Mariel
dc.contributor.authorEtcheverry, Lorena
dc.contributor.authorFonck Larraín, Antonia
dc.contributor.authorGrez, Alejandro
dc.contributor.authorMery Quiroz, Domingo Arturo
dc.contributor.authorReutter de la Maza, Juan Lorenzo
dc.contributor.authorRojas, Hugo
dc.date.accessioned2025-03-19T15:41:31Z
dc.date.available2025-03-19T15:41:31Z
dc.date.issued2024
dc.description.abstractWe present our results regarding the construction of a knowledge graph from historical documents related to the Chilean dictatorship period (1973-1990). Our approach uses LLMs to automatically recognize entities and relations between them and resolve conflicts between these values. To prevent hallucination, the interaction with the LLM is grounded in a simple ontology with four types of entities and seven types of relations. To evaluate our architecture, we use a gold standard graph constructed using a small subset of the documents, and compare this to the graph obtained from our approach when processing the same set of documents. Results show that the automatic construction manages to recognize a good portion of all the entities in the gold standard and that those not recognized are explained mainly by the level of granularity in which the information is structured in the graph and not because the automatic approach misses an important entity in the graph. Looking forward, we expect this report to encourage work on other similar projects focused on enhancing research in humanities and social science. However, we remark that better evaluation metrics are needed to accurately fine-tune these types of architectures.
dc.fechaingreso.objetodigital2025-03-19
dc.format.extent11 páginas
dc.fuente.origenScopus
dc.identifier.issn1613-0073
dc.identifier.scopusidScopus_ID: 85212705684
dc.identifier.urihttps://doi.org/10.48550/arXiv.2408.11975
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/102816
dc.information.autorucInstituto de Historia; Fonck Larraín, Antonia; S/I; 206608
dc.information.autorucEscuela de Ingeniería; Dunstan Escudero, Jocelyn Mariel; S/I; 1285723
dc.information.autorucEscuela de Ingeniería; Mery Quiroz, Domingo Arturo; 0000-0003-4748-3882; 102382
dc.information.autorucEscuela de Ingeniería; Reutter de la Maza, Juan Lorenzo; 0000-0002-2186-0312; 126898
dc.language.isoen
dc.nota.accesocontenido completo
dc.relation.ispartofWorkshop on Knowledge Base Construction from Pre-Trained Language Models and the 3rd Challenge on Language Models for Knowledge Base Construction, KBC-LM-LM-KBC : 2nd : 2024 : Baltimore, EE.UU
dc.revistaCEUR Workshop Proceedings
dc.rightsacceso abierto
dc.rights.licenseCC BY Atribución Internacional 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleAutomatic knowledge-graph creation from historical documents: The Chilean dictatorship as a case study
dc.typepreprint
dc.volumen3853
sipa.codpersvinculados206608
sipa.codpersvinculados1285723
sipa.codpersvinculados102382
sipa.codpersvinculados126898
sipa.trazabilidadScopus;2025-01-05
sipa.trazabilidadORCID;2025-03-03
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2408.11975v1.pdf
Size:
1.19 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de conferencia