{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4111"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4111","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Improving Relation Extraction from Unstructured Genealogical Texts Using Fine-Tuned Transformers","abstract":"Though exploring one’s family lineage through genealogical family trees can be insightful to developing one’s identity, this knowledge is typically held behind closed doors by private companies or require expensive technologies, such as DNA testing, to uncover. With the ever-booming explosion of data on the world wide web, many unstructured text documents, both old and new, are being discovered, written, and processed which contain rich genealogical information. With access to this immense amount of data, however, entails a costly process whereby people, typically volunteers, have to read large amounts of text to find relationships between people. This delays having genealogical information be open and accessible to all. This thesis explores state-of-the-art methods for relation extraction across the genealogical and biomedical domains and bridges new and old research by proposing an updated three-tier system for parsing unstructured documents. This system makes use of recently developed and massively pretrained transformers and fine-tuning techniques to take advantage of these deep neural models’ inherent understanding of English syntax and semantics for classification. With only a fraction of labeled data typically needed to train large models, fine-tuning a LUKE relation classification model with minimal added features can identify genealogical relationships with macro precision, recall, and F1 scores of 0.880, 0.867, and 0.871, respectively, in data sets with scarce (∼10%) positive relations. Further- more, with the advent of a modern coreference resolution system utilizing SpanBERT embeddings and a modern named entity parser, our end-to-end pipeline can extract and correctly classify relationships within unstructured documents with macro precision, recall, and F1 scores of 0.794, 0.616, and 0.676, respectively. This thesis also evaluates individual components of the system and discusses future improvements to be made.","abstract_html":"Though exploring one’s family lineage through genealogical family trees can be insightful to developing one’s identity, this knowledge is typically held behind closed doors by private companies or require expensive technologies, such as DNA testing, to uncover. With the ever-booming explosion of data on the world wide web, many unstructured text documents, both old and new, are being discovered, written, and processed which contain rich genealogical information. With access to this immense amount of data, however, entails a costly process whereby people, typically volunteers, have to read large amounts of text to find relationships between people. This delays having genealogical information be open and accessible to all. This thesis explores state-of-the-art methods for relation extraction across the genealogical and biomedical domains and bridges new and old research by proposing an updated three-tier system for parsing unstructured documents. This system makes use of recently developed and massively pretrained transformers and fine-tuning techniques to take advantage of these deep neural models’ inherent understanding of English syntax and semantics for classification. With only a fraction of labeled data typically needed to train large models, fine-tuning a LUKE relation classification model with minimal added features can identify genealogical relationships with macro precision, recall, and F1 scores of 0.880, 0.867, and 0.871, respectively, in data sets with scarce (∼10%) positive relations. Further- more, with the advent of a modern coreference resolution system utilizing SpanBERT embeddings and a modern named entity parser, our end-to-end pipeline can extract and correctly classify relationships within unstructured documents with macro precision, recall, and F1 scores of 0.794, 0.616, and 0.676, respectively. This thesis also evaluates individual components of the system and discusses future improvements to be made.","abstract_has_math":false,"creators":["Parrolivelli, Carloangello"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Lubomir Stanchev","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:03Z","subjects":["Relation Extraction","Genealogical Relations","Transformers","Unstructured Text","Machine Learning","Natural Language Processing","Other Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2022.78"],"render_values":[{"text":"10.15368/theses.2022.78","href":"https://doi.org/10.15368/theses.2022.78","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2561","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/2561","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4111","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lubomir Stanchev","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Parrolivelli, Carloangello"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2022-06-10T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2022-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Relation Extraction","Genealogical Relations","Transformers","Unstructured Text","Machine Learning","Natural Language Processing","Other Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2561","10.15368/theses.2022.78"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Though exploring one’s family lineage through genealogical family trees can be insightful to developing one’s identity, this knowledge is typically held behind closed doors by private companies or require expensive technologies, such as DNA testing, to uncover. With the ever-booming explosion of data on the world wide web, many unstructured text documents, both old and new, are being discovered, written, and processed which contain rich genealogical information. With access to this immense amount of data, however, entails a costly process whereby people, typically volunteers, have to read large amounts of text to find relationships between people. This delays having genealogical information be open and accessible to all. This thesis explores state-of-the-art methods for relation extraction across the genealogical and biomedical domains and bridges new and old research by proposing an updated three-tier system for parsing unstructured documents. This system makes use of recently developed and massively pretrained transformers and fine-tuning techniques to take advantage of these deep neural models’ inherent understanding of English syntax and semantics for classification. With only a fraction of labeled data typically needed to train large models, fine-tuning a LUKE relation classification model with minimal added features can identify genealogical relationships with macro precision, recall, and F1 scores of 0.880, 0.867, and 0.871, respectively, in data sets with scarce (∼10%) positive relations. Further- more, with the advent of a modern coreference resolution system utilizing SpanBERT embeddings and a modern named entity parser, our end-to-end pipeline can extract and correctly classify relationships within unstructured documents with macro precision, recall, and F1 scores of 0.794, 0.616, and 0.676, respectively. This thesis also evaluates individual components of the system and discusses future improvements to be made."]},{"key":"dc:title","label":"Title","values":["Improving Relation Extraction from Unstructured Genealogical Texts Using Fine-Tuned Transformers"]}]}],"canonical_facts":{"dc:contributor":["Lubomir Stanchev","Computer Science","College of Engineering"],"dc:creator":["Parrolivelli, Carloangello"],"dc:date.available":["2022-06-10T07:00:00Z"],"dc:date.created":["2022-06-01T07:00:00Z"],"dc:description.abstract":["Though exploring one’s family lineage through genealogical family trees can be insightful to developing one’s identity, this knowledge is typically held behind closed doors by private companies or require expensive technologies, such as DNA testing, to uncover. With the ever-booming explosion of data on the world wide web, many unstructured text documents, both old and new, are being discovered, written, and processed which contain rich genealogical information. With access to this immense amount of data, however, entails a costly process whereby people, typically volunteers, have to read large amounts of text to find relationships between people. This delays having genealogical information be open and accessible to all. This thesis explores state-of-the-art methods for relation extraction across the genealogical and biomedical domains and bridges new and old research by proposing an updated three-tier system for parsing unstructured documents. This system makes use of recently developed and massively pretrained transformers and fine-tuning techniques to take advantage of these deep neural models’ inherent understanding of English syntax and semantics for classification. With only a fraction of labeled data typically needed to train large models, fine-tuning a LUKE relation classification model with minimal added features can identify genealogical relationships with macro precision, recall, and F1 scores of 0.880, 0.867, and 0.871, respectively, in data sets with scarce (∼10%) positive relations. Further- more, with the advent of a modern coreference resolution system utilizing SpanBERT embeddings and a modern named entity parser, our end-to-end pipeline can extract and correctly classify relationships within unstructured documents with macro precision, recall, and F1 scores of 0.794, 0.616, and 0.676, respectively. This thesis also evaluates individual components of the system and discusses future improvements to be made."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2561","10.15368/theses.2022.78"],"dc:subject":["Relation Extraction","Genealogical Relations","Transformers","Unstructured Text","Machine Learning","Natural Language Processing","Other Computer Engineering"],"dc:title":["Improving Relation Extraction from Unstructured Genealogical Texts Using Fine-Tuned Transformers"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:12:03Z"}