{"id":{"repo_id":"gatech","oai_identifier":"oai:repository.gatech.edu:1853/76745"},"canonical_url":"https://search.ndltd.org/etd/gatech/oai:repository.gatech.edu:1853/76745","repository":{"repo_id":"gatech","name":"Georgia Tech","base_url":"https://repository.gatech.edu/server/oai/request"},"display":{"title":"A pipeline for data and knowledge extraction from material science literature to accelerate scientific discovery","abstract":"Scientific literature is growing at an exponential pace which makes it difficult for scientists to search through and effectively utilize the data contained in it. In this work, we developed methods and data sets needed to extract knowledge and material property data from a corpus of 2.4 million materials science articles. We uniquely identified extracted polymer materials by training supervised clustering models using parameterized cosine distances with hierarchical agglomerative clustering that achieve state-of-the-art results on a benchmark data set of polymer named entity clusters. In addition, we built sequence labeling models that can tag property information using an ontology specific to the materials domain. MaterialsBERT, a pre-trained encoder fine-tuned on the aforementioned corpus of materials science papers was used as the encoder for the sequence labeling model and outperforms the baselines tested for data sets in the materials domain. We developed two pipelines, one that combines sequence labeling outputs with heuristic rules, and another using prompts to a large language model, to extract material property records from our corpus of papers. The extracted data is made available to the public through the interface polymerscholar.org. A subset of the extracted data was used to train machine learning models to predict the power conversion efficiency of polymer solar cells, thus demonstrating an end-to-end pipeline that goes from literature-extracted data to data-driven insights. This work will reduce the time taken during the search as well as the discovery phase of experimental work, thus allowing researchers to move beyond an Edisonian trial-and-error approach.","abstract_html":"Scientific literature is growing at an exponential pace which makes it difficult for scientists to search through and effectively utilize the data contained in it. In this work, we developed methods and data sets needed to extract knowledge and material property data from a corpus of 2.4 million materials science articles. We uniquely identified extracted polymer materials by training supervised clustering models using parameterized cosine distances with hierarchical agglomerative clustering that achieve state-of-the-art results on a benchmark data set of polymer named entity clusters. In addition, we built sequence labeling models that can tag property information using an ontology specific to the materials domain. MaterialsBERT, a pre-trained encoder fine-tuned on the aforementioned corpus of materials science papers was used as the encoder for the sequence labeling model and outperforms the baselines tested for data sets in the materials domain. We developed two pipelines, one that combines sequence labeling outputs with heuristic rules, and another using prompts to a large language model, to extract material property records from our corpus of papers. The extracted data is made available to the public through the interface polymerscholar.org. A subset of the extracted data was used to train machine learning models to predict the power conversion efficiency of polymer solar cells, thus demonstrating an end-to-end pipeline that goes from literature-extracted data to data-driven insights. This work will reduce the time taken during the search as well as the discovery phase of experimental work, thus allowing researchers to move beyond an Edisonian trial-and-error approach.","abstract_has_math":false,"creators":["Shetty, Pranav"],"institution":"Georgia Institute of Technology","degree_name":null,"degree_level":"Doctoral","degree_discipline":null,"degree_department":"Computational Science and Engineering","school":null,"contributors":[],"advisors":["Ramprasad, Rampi","Zhang, Chao"],"committee_chairs":[],"committee_members":["Ritter, Alan","Joseph, Roshan","Jang, Seung Soon"],"year":2023,"date_issued":"2023-08-16","date_published":"2023-08-16","updated_at":"2026-11-19T04:25:43Z","subjects":["Natural Language Processing","Information Extraction","Materials Science","Polymers","Polymer Solar Cells"],"languages":["en_US"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1853/76745","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/1853/76745","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://repository.gatech.edu/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Arepository.gatech.edu%3A1853%2F76745","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ramprasad, Rampi","Zhang, Chao"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Ritter, Alan","Joseph, Roshan","Jang, Seung Soon"]},{"key":"dc:contributor.department","label":"Department","values":["Computational Science and Engineering"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["College of Computing","School of Computational Science and Engineering"]},{"key":"dc:creator","label":"Author","values":["Shetty, Pranav"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-01-15T13:31:02Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-01-15T13:31:02Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2023-12"]},{"key":"dc:date.issued","label":"Date","values":["2023-08-16"]},{"key":"dc:date.submitted","label":"Dc Date Submitted","values":["December 2023"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2025-01-15T13:31:03Z"]},{"key":"dc:publisher","label":"Institution","values":["Georgia Institute of Technology"]},{"key":"dc:relation.advisorentity","label":"Dc Relation Advisorentity","values":["04cb4ec4-0497-4200-9647-d434cd2c2476","56737267-494f-4a81-bdf3-a271680c1bf1"]},{"key":"dc:relation.ispartofseries","label":"Dc Relation Ispartofseries","values":["Doctor of Philosophy with a Major in Machine Learning"]},{"key":"dc:relation.orgunit","label":"Dc Relation Orgunit","values":["c8892b3c-8db6-4b7b-a33a-1b67f7db2021","01ab2ef1-c6da-49c9-be98-fbd1d840d2b1"]},{"key":"dc:relation.seriesentity","label":"Dc Relation Seriesentity","values":["76f5c118-19fc-4530-bd69-7df1110d8ec5"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_program","label":"Thesis Degree Program","values":["Machine Learning"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Natural Language Processing","Information Extraction","Materials Science","Polymers","Polymer Solar Cells"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1853/76745"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Scientific literature is growing at an exponential pace which makes it difficult for scientists to search through and effectively utilize the data contained in it. In this work, we developed methods and data sets needed to extract knowledge and material property data from a corpus of 2.4 million materials science articles. We uniquely identified extracted polymer materials by training supervised clustering models using parameterized cosine distances with hierarchical agglomerative clustering that achieve state-of-the-art results on a benchmark data set of polymer named entity clusters. In addition, we built sequence labeling models that can tag property information using an ontology specific to the materials domain. MaterialsBERT, a pre-trained encoder fine-tuned on the aforementioned corpus of materials science papers was used as the encoder for the sequence labeling model and outperforms the baselines tested for data sets in the materials domain. We developed two pipelines, one that combines sequence labeling outputs with heuristic rules, and another using prompts to a large language model, to extract material property records from our corpus of papers. The extracted data is made available to the public through the interface polymerscholar.org. A subset of the extracted data was used to train machine learning models to predict the power conversion efficiency of polymer solar cells, thus demonstrating an end-to-end pipeline that goes from literature-extracted data to data-driven insights. This work will reduce the time taken during the search as well as the discovery phase of experimental work, thus allowing researchers to move beyond an Edisonian trial-and-error approach."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["A pipeline for data and knowledge extraction from material science literature to accelerate scientific discovery"]},{"key":"dspace:entity.type","label":"Dspace Entity Type","values":["Publication"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ramprasad, Rampi","Zhang, Chao"],"dc:contributor.committeemember":["Ritter, Alan","Joseph, Roshan","Jang, Seung Soon"],"dc:contributor.department":["Computational Science and Engineering"],"dc:contributor.other":["College of Computing","School of Computational Science and Engineering"],"dc:creator":["Shetty, Pranav"],"dc:date.accessioned":["2025-01-15T13:31:02Z"],"dc:date.available":["2025-01-15T13:31:02Z"],"dc:date.created":["2023-12"],"dc:date.issued":["2023-08-16"],"dc:date.submitted":["December 2023"],"dc:date.updated":["2025-01-15T13:31:03Z"],"dc:description.abstract":["Scientific literature is growing at an exponential pace which makes it difficult for scientists to search through and effectively utilize the data contained in it. In this work, we developed methods and data sets needed to extract knowledge and material property data from a corpus of 2.4 million materials science articles. We uniquely identified extracted polymer materials by training supervised clustering models using parameterized cosine distances with hierarchical agglomerative clustering that achieve state-of-the-art results on a benchmark data set of polymer named entity clusters. In addition, we built sequence labeling models that can tag property information using an ontology specific to the materials domain. MaterialsBERT, a pre-trained encoder fine-tuned on the aforementioned corpus of materials science papers was used as the encoder for the sequence labeling model and outperforms the baselines tested for data sets in the materials domain. We developed two pipelines, one that combines sequence labeling outputs with heuristic rules, and another using prompts to a large language model, to extract material property records from our corpus of papers. The extracted data is made available to the public through the interface polymerscholar.org. A subset of the extracted data was used to train machine learning models to predict the power conversion efficiency of polymer solar cells, thus demonstrating an end-to-end pipeline that goes from literature-extracted data to data-driven insights. This work will reduce the time taken during the search as well as the discovery phase of experimental work, thus allowing researchers to move beyond an Edisonian trial-and-error approach."],"dc:description.degree":["Ph.D."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/1853/76745"],"dc:language.iso":["en_US"],"dc:publisher":["Georgia Institute of Technology"],"dc:relation.advisorentity":["04cb4ec4-0497-4200-9647-d434cd2c2476","56737267-494f-4a81-bdf3-a271680c1bf1"],"dc:relation.ispartofseries":["Doctor of Philosophy with a Major in Machine Learning"],"dc:relation.orgunit":["c8892b3c-8db6-4b7b-a33a-1b67f7db2021","01ab2ef1-c6da-49c9-be98-fbd1d840d2b1"],"dc:relation.seriesentity":["76f5c118-19fc-4530-bd69-7df1110d8ec5"],"dc:subject":["Natural Language Processing","Information Extraction","Materials Science","Polymers","Polymer Solar Cells"],"dc:title":["A pipeline for data and knowledge extraction from material science literature to accelerate scientific discovery"],"dc:type":["Text","Dissertation"],"dspace:entity.type":["Publication"],"thesis:degree_level":["Doctoral"],"thesis:degree_program":["Machine Learning"]},"updated_at":"2026-11-19T04:25:43Z"}