{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T10:54:01Z","timestamp":1768388041444,"version":"3.49.0"},"reference-count":54,"publisher":"China Science Publishing & Media Ltd.","issue":"1","license":[{"start":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T00:00:00Z","timestamp":1710115200000},"content-version":"vor","delay-in-days":70,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,2,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n               <jats:p>Knowledge graphs are employed in several tasks, such as question answering and recommendation systems, due to their ability to represent relationships between concepts. Automatically constructing such a graphs, however, remains an unresolved challenge within knowledge representation. To tackle this challenge, we propose CtxKG, a method specifically aimed at extracting knowledge graphs in a context of limited resources in which the only input is a set of unstructured text documents. CtxKG is based on OpenIE (a relationship triple extraction method) and BERT (a language model) and contains four stages: the extraction of relationship triples directly from text; the identification of synonyms across triples; the merging of similar entities; and the building of bridges between knowledge graphs of different documents. Our method distinguishes itself from those in the current literature (i) through its use of the parse tree to avoid the overlapping entities produced by base implementations of OpenIE; and (ii) through its bridges, which create a connected network of graphs, overcoming a limitation similar methods have of one isolated graph per document. We compare our method to two others by generating graphs for movie articles from Wikipedia and contrasting them with benchmark graphs built from the OMDb movie database. Our results suggest that our method is able to improve multiple aspects of knowledge graph construction. They also highlight the critical role that triple identification and named-entity recognition have in improving the quality of automatically generated graphs, suggesting future paths for investigation. Finally, we apply CtxKG to build BlabKG, a knowledge graph for the Blue Amazon, and discuss possible improvements.<\/jats:p>","DOI":"10.1162\/dint_a_00223","type":"journal-article","created":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T20:09:27Z","timestamp":1710187767000},"page":"64-103","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":5,"title":["Applying a Context-based Method to Build a Knowledge Graph for the Blue Amazon"],"prefix":"10.3724","volume":"6","author":[{"given":"Pedro de Moraes","family":"Ligabue","sequence":"first","affiliation":[{"name":"Escola Polit\u00e9cnica, Universidade de S\u00e3o Paulo, Rua Visconde da Luz, 60, S\u00e3o Paulo, S\u00e3o Paulo 05508-010, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anarosa Alves Franco","family":"Brand\u00e3o","sequence":"additional","affiliation":[{"name":"Escola Polit\u00e9cnica, Universidade de S\u00e3o Paulo, Av. Prof. Luciano Gualberto, tv 3, 158, S\u00e3o Paulo 05508-010, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarajane Marques","family":"Peres","sequence":"additional","affiliation":[{"name":"Escola de Artes Ci\u00eancias e Humanidades, Universidade de S\u00e3o Paulo, Rua Arlindo B\u00e9ttio, 1000, S\u00e3o Paulo 03828-000, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio Gagliardi","family":"Cozman","sequence":"additional","affiliation":[{"name":"Escola Polit\u00e9cnica, Universidade de S\u00e3o Paulo, Av. Prof. Luciano Gualberto, tv 3, 158, S\u00e3o Paulo 05508-010, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paulo","family":"Pirozelli","sequence":"additional","affiliation":[{"name":"Instituto de Estudos Avan\u00e7ados, Universidade de S\u00e3o Paulo, Rua da Pra\u00e7a do Rel\u00f3gio, 109, S\u00e3o Paulo 05508-050, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2026","published-online":{"date-parts":[[2024,2,1]]},"reference":[{"key":"2024041719553154500_ref1","volume-title":"What Is a knowledge graph?","author":"IBM Cloud Education","year":"2021"},{"key":"2024041719553154500_ref2","volume-title":"Introducing the knowledge graph: Things, not strings","author":"Singhal","year":"2012"},{"key":"2024041719553154500_ref3","doi-asserted-by":"publisher","first-page":"1540","DOI":"10.1109\/ICDM.2019.00204","volume-title":"Automatic knowledge graph construction: A report on the 2019 ICDM\/ICBK contest","author":"Wu","year":". 2019"},{"issue":"5","key":"2024041719553154500_ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3453651","article-title":"Developing a Vietnamese tourism question answering system using knowledge graph and deep learning","volume":"20","author":"Do","year":". 2021","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"issue":"8","key":"2024041719553154500_ref5","doi-asserted-by":"publisher","first-page":"10620","DOI":"10.1007\/s11227-021-04212-6","article-title":"Knowledge-based virtual outdoor weather event simulator using Unity 3D","volume":"78","author":"Noueihed","year":"2022","journal-title":"J. Supercomput."},{"issue":"2","key":"2024041719553154500_ref6","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1109\/tnnls.2021.3070843","article-title":"A survey on knowledge graphs: Representation, acquisition, and applications","volume":"33","author":"Ji","year":". 2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2024041719553154500_ref7","volume-title":"Knowledge Panel Help, About knowledge panels"},{"key":"2024041719553154500_ref8","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","article-title":"Wikidata: A free collaborative knowledgebase","volume":"57","author":"Vrande\u010di\u0107","year":"10 . 2014","journal-title":"Communications of the ACM"},{"key":"2024041719553154500_ref9","article-title":"Constructing a knowledge graph from unstructured documents without external alignment","volume":"abs\/2008.08995","author":"Yu","year":"2020","journal-title":"CoRR"},{"key":"2024041719553154500_ref10","volume-title":"Wikidata statistics","author":"Wikimedia"},{"key":"2024041719553154500_ref11","doi-asserted-by":"publisher","first-page":"2124","DOI":"10.18653\/v1\/P16-1200","article-title":"Neural relation extraction with selective attention over instances","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Lin","year":". 2016"},{"key":"2024041719553154500_ref12","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.18653\/v1\/D16-1147","article-title":"Key-value memory networks for directly reading documents","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Miller","year":". 2016"},{"key":"2024041719553154500_ref13","volume-title":"Convention on the law of the sea","author":"United Nations General Assembly","year":". 1982"},{"key":"2024041719553154500_ref14","volume-title":"The Blue Amazon: Brazil Asserts Its Influence Across the Atlantic","author":"Thompson","year":". 2015"},{"key":"2024041719553154500_ref15","volume-title":"The Blue Amazon, Brazil's New Natural Resources Frontier","author":"Ortiz","year":"2015"},{"key":"2024041719553154500_ref16","article-title":"Flying Blind","volume-title":"Pre-Salt Oil Fields","author":"Frayssinet","year":". 2011"},{"key":"2024041719553154500_ref17","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/ICKG55886.2022.00028","article-title":"BlabKG: A knowledge graph for the Blue Amazon","volume-title":"2022 IEEE International Conference on Knowledge Graph (ICKG)","author":"de Moraes Ligabue","year":"2022"},{"issue":"5","key":"2024041719553154500_ref18","doi-asserted-by":"publisher","first-page":"2254","DOI":"10.1109\/TKDE.2020.3014166","article-title":"KGGen: A generative approach for incipient knowledge graph population","volume":"34","author":"Chen","year":"2022","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2024041719553154500_ref19","first-page":"2145","article-title":"A survey on recent advances in named entity recognition from deep learning models","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Yadav","year":". 2018"},{"issue":"05","key":"2024041719553154500_ref20","doi-asserted-by":"publisher","first-page":"9314","DOI":"10.1609\/aaai.v34i05.6471","article-title":"Joint entity and relation extraction with a hybrid transformer and reinforcement learning based model","volume":"34","author":"Xiao","year":". 2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2024041719553154500_ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1705.00108","volume-title":"Semi-supervised sequence tagging with bidirectional language models","author":"Peters","year":"2017"},{"key":"2024041719553154500_ref22","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"2024041719553154500_ref23","doi-asserted-by":"publisher","first-page":"12467","DOI":"10.1109\/ACCESS.2019.2891770","article-title":"A single attention-based combination of cnn and rnn for relation classification","volume":"7","author":"Guo","year":"2019","journal-title":"IEEE Access"},{"issue":"11","key":"2024041719553154500_ref24","doi-asserted-by":"publisher","first-page":"8393","DOI":"10.1007\/s00521-020-05495-1","article-title":"Building a knowledge graph by using cross-lingual transfer method and distributed MinIE algorithm on Apache Spark","volume":"34","author":"Do","year":". 2022","journal-title":"Neural Comput. Appl."},{"key":"2024041719553154500_ref25","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1145\/2488388.2488420","article-title":"ClausIE: Clause-based open information extraction","volume-title":"Proceedings of the 22nd International Conference on World Wide Web, ser. WWW \u201813","author":"Corro","year":"2013"},{"key":"2024041719553154500_ref26","doi-asserted-by":"publisher","first-page":"2630","DOI":"10.18653\/v1\/D17-1278","article-title":"MinIE: Minimizing facts in open information extraction","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Gashteovski","year":". 2017"},{"key":"2024041719553154500_ref27","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.inffus.2020.01.010","article-title":"Anaphora and coreference resolution: A review","volume":"59","author":"Sukthanker","year":"2020","journal-title":"Information Fusion"},{"key":"2024041719553154500_ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.07045","volume-title":"End-to-end neural coreference resolution","author":"Lee","year":"2017"},{"key":"2024041719553154500_ref29","article-title":"Translating embeddings formodelingmulti-relational data","volume-title":"Advances in Neural Information Processing Systems","author":"Bordes","year":"2013"},{"key":"2024041719553154500_ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.03954","volume-title":"Multilingual knowledge graph embeddings for cross-lingual knowledge alignment","author":"Chen","year":"2016"},{"key":"2024041719553154500_ref31","first-page":"4258","article-title":"Iterative entity alignment via joint knowledge embeddings","volume-title":"Proceedings of the 26th International Joint Conference on Artificial Intelligence, ser. IJCAI\u201917","author":"Zhu","year":"2017"},{"key":"2024041719553154500_ref32","doi-asserted-by":"publisher","first-page":"349","DOI":"10.18653\/v1\/D18-1032","article-title":"Cross-lingual knowledge graph alignment via graph convolutional networks","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Wang","year":". 2018"},{"key":"2024041719553154500_ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/733","article-title":"Relation-aware entity alignment for heterogeneous knowledge graphs","volume-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, International Joint Conferences on Artificial Intelligence Organization","author":"Wu","year":". 2019"},{"key":"2024041719553154500_ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2012.08128","volume-title":"Relation-aware neighborhood matching model for entity alignment","author":"Zhu","year":"2020"},{"key":"2024041719553154500_ref35","doi-asserted-by":"publisher","first-page":"192435","DOI":"10.1109\/ACCESS.2020.3030076","article-title":"Knowledge graph completion: A review","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"2024041719553154500_ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1703.06103","volume-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2017"},{"key":"2024041719553154500_ref37","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TransAI54797.2022.00031","article-title":"Graph embedding: A methodological survey","volume-title":"2022 Fourth International Conference on Transdisciplinary AI (TransAI)","author":"Barr","year":"2022"},{"key":"2024041719553154500_ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1607.00653","volume-title":"node2vec: Scalable feature learning for networks","author":"Grover","year":"2016"},{"key":"2024041719553154500_ref39","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3115\/v1\/P14-5010","article-title":"The Stanford CoreNLP natural language processing toolkit","volume-title":"Proceedings of 52 nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Manning","year":"."},{"key":"2024041719553154500_ref40","first-page":"2670","article-title":"Open information extraction from the web","volume-title":"Proceedings of the 20th International Joint Conference on Artificial Intelligence, ser. IJCAI\u201907","author":"Banko","year":"2007"},{"key":"2024041719553154500_ref41","doi-asserted-by":"publisher","first-page":"169","DOI":"10.18653\/v1\/D19-3029","article-title":"OpenNRE: An open and extensible toolkit for neural relation extraction","volume-title":"Proceedings of EMNLP-IJCNLP: System Demonstrations","author":"Han","year":"2019"},{"key":"2024041719553154500_ref42","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.18653\/v1\/2020.findings-emnlp.99","article-title":"Multi2OIE: Multilingual open information extraction based on multi-head attention with BERT","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Ro","year":". 2020"},{"key":"2024041719553154500_ref43","first-page":"4585","article-title":"Universal Stanford Dependencies: A crosslinguistic typology","volume-title":"Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914)","author":"de Marneffe","year":"2014"},{"key":"2024041719553154500_ref44","volume-title":"API: parsing wikitext\u2014MediaWiki","author":"MediaWiki","year":"2022"},{"key":"2024041719553154500_ref45","doi-asserted-by":"publisher","first-page":"1768","DOI":"10.1145\/3404835.3463019","article-title":"Revisiting the tag relevance prediction problem","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, ser. SIGIR \u201821, Virtual Event","author":"Kotkov","year":"2021"},{"issue":"3","key":"2024041719553154500_ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2362394.2362395","article-title":"The tag genome: Encoding community knowledge to support novel interaction","volume":"2","author":"Vig","year":". 2012","journal-title":"ACM Trans. Interact. Intell. Syst."},{"key":"2024041719553154500_ref47","doi-asserted-by":"publisher","first-page":"4544","DOI":"10.1145\/3459637.3482012","article-title":"Pir\u00e1: A bilingual Portuguese-English dataset for question-answering about the ocean","volume-title":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management, ser. CIKM \u201821, Virtual Event","author":"Paschoal","year":"2021"},{"issue":"5","key":"2024041719553154500_ref48","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1190\/tle31050546.1","article-title":"Extracting full-resolution models from seismic data to minimize systematic errors in inversion: Method and examples","volume":"31","author":"Brouwer","year":"2012","journal-title":"The Leading Edge"},{"key":"2024041719553154500_ref49","doi-asserted-by":"publisher","DOI":"10.4043\/10722-MS","article-title":"Deepwater Installation of a Large Capacity FPSO with Large Number of Risers in the Marlim Field, vol. All Days","volume-title":"OTC Offshore Technology Conference, OTC-10722-MS","year":"1999"},{"key":"2024041719553154500_ref50","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.marpetgeo.2020.104805","article-title":"Petrography, geochemistry and origin of South Atlantic evaporites: The Brazilian side","volume":"127","author":"Szatmari","year":"2021","journal-title":"Marine and Petroleum Geology"},{"key":"2024041719553154500_ref51","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.scitotenv.2019.05.126","article-title":"Arsenic enrichment in sediments and beaches of Brazilian coastal waters: A review","volume":"681","author":"Baeyens","year":"2019","journal-title":"Science of The Total Environment"},{"key":"2024041719553154500_ref52","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.chemgeo.2019.119457","article-title":"Environmental conditions of deposition of the Lower Cretaceous lacustrine carbonates of the Barra Velha formation, Santos Basin (Brazil), based on stable carbon and oxygen isotopes: A continental record of pCO2 during the onset of the Oceanic Anoxic Event 1a (OAE 1a) interval?","volume":"535","author":"Pietzsch","year":"2020","journal-title":"Chemical Geology"},{"key":"2024041719553154500_ref53","volume-title":"Br\u00e9sil-ZEE et plateau continental.jpeg \u2014 Wikimedia Commons, the free media repository","author":"Wikimedia Commons, File"},{"issue":"2","key":"2024041719553154500_ref54","first-page":"313","article-title":"Building a large annotated corpus of English: The Penn Treebank","volume":"19","author":"Marcus","year":"1993","journal-title":"Computational Linguistics"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/6\/1\/64\/2364189\/dint_a_00223.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/6\/1\/64\/2364189\/dint_a_00223.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T07:41:02Z","timestamp":1741938062000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.1162\/dint_a_00223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":54,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2,1]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00223","relation":{},"ISSN":["2641-435X"],"issn-type":[{"value":"2641-435X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}