{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T06:48:35Z","timestamp":1767422915568,"version":"build-2065373602"},"reference-count":72,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:00:00Z","timestamp":1750291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003141","name":"SECIHTI","doi-asserted-by":"publisher","award":["CF-2023-I-2854"],"award-info":[{"award-number":["CF-2023-I-2854"]}],"id":[{"id":"10.13039\/501100003141","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Instituto Nacional de Enfermedades Respiratorias Ismael Cos\u00edo Villegas","award":["CF-2023-I-2854"],"award-info":[{"award-number":["CF-2023-I-2854"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Large-language-model (LLM) APIs demonstrate impressive reasoning capabilities, but their size, cost, and closed weights limit the deployment of knowledge-aware AI within biomedical research groups. At the other extreme, standard attention-based neural language models (SANLMs)\u2014including encoder\u2013decoder architectures such as Transformers, Gated Recurrent Units (GRUs), and Long Short-Term Memory (LSTM) networks\u2014are computationally inexpensive. However, their capacity for semantic reasoning in noisy, open-vocabulary knowledge bases (KBs) remains unquantified. Therefore, we investigate whether compact SANLMs can (i) reason over hybrid OpenIE-derived KBs that integrate commonsense, general-purpose, and non-communicable-disease (NCD) literature; (ii) operate effectively on commodity GPUs; and (iii) exhibit semantic coherence as assessed through manual linguistic inspection. To this end, we constructed four training KBs by integrating ConceptNet (600k triples), a 39k-triple general-purpose OpenIE set, and an 18.6k-triple OpenNCDKB extracted from 1200 PubMed abstracts. Encoder\u2013decoder GRU, LSTM, and Transformer models (1\u20132 blocks) were trained to predict the object phrase given the subject + predicate. Beyond token-level cross-entropy, we introduced the Meaning-based Selectional-Preference Test (MSPT): for each withheld triple, we masked the object, generated a candidate, and measured its surplus cosine similarity over a random baseline using word embeddings, with significance assessed via a one-sided t-test. Hyperparameter sensitivity (311 GRU\/168 LSTM runs) was analyzed, and qualitative frame\u2013role diagnostics completed the evaluation. Our results showed that all SANLMs learned effectively from the point of view of the cross entropy loss. In addition, our MSPT provided meaningful semantic insights: for the GRUs (256-dim, 2048-unit, 1-layer): mean similarity (\u03bcsts) of 0.641 to the ground truth vs. 0.542 to the random baseline (gap 12.1%; p&lt;10\u2212180). For the 1-block Transformer: \u03bcsts=0.551 vs. 0.511 (gap 4%; p&lt;10\u221225). While Transformers minimized loss and accuracy variance, GRUs captured finer selectional preferences. Both architectures trained within &lt;24 GB GPU VRAM and produced linguistically acceptable, albeit over-generalized, biomedical assertions. Due to their observed performance, LSTM results were designated as baseline models for comparison. Therefore, properly tuned SANLMs can achieve statistically robust semantic reasoning over noisy, domain-specific KBs without reliance on massive LLMs. Their interpretability, minimal hardware footprint, and open weights promote equitable AI research, opening new avenues for automated NCD knowledge synthesis, surveillance, and decision support.<\/jats:p>","DOI":"10.3390\/bdcc9060162","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T09:57:48Z","timestamp":1750327068000},"page":"162","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Semantic Reasoning Using Standard Attention-Based Models: An Application to Chronic Disease Literature"],"prefix":"10.3390","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6400-0526","authenticated-orcid":false,"given":"Yalbi Itzel","family":"Balderas-Mart\u00ednez","sequence":"first","affiliation":[{"name":"Instituto Nacional de Enfermedades Respiratorias (INER) Ismael Cos\u00edo Villegas, Ciudad de M\u00e9xico 14080, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3248-2652","authenticated-orcid":false,"given":"Jos\u00e9 Armando","family":"S\u00e1nchez-Rojas","sequence":"additional","affiliation":[{"name":"Graduate Studies Division, Universidad Tecnol\u00f3gica de la Mixteca, Huajuapan de Le\u00f3n 69000, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0787-7417","authenticated-orcid":false,"given":"Arturo","family":"T\u00e9llez-Vel\u00e1zquez","sequence":"additional","affiliation":[{"name":"Graduate Studies Division, Universidad Tecnol\u00f3gica de la Mixteca, Huajuapan de Le\u00f3n 69000, Mexico"}]},{"given":"Flavio","family":"Ju\u00e1rez Mart\u00ednez","sequence":"additional","affiliation":[{"name":"Graduate Studies Division, Universidad Tecnol\u00f3gica de la Mixteca, Huajuapan de Le\u00f3n 69000, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5494-7027","authenticated-orcid":false,"given":"Ra\u00fal","family":"Cruz-Barbosa","sequence":"additional","affiliation":[{"name":"Graduate Studies Division, Universidad Tecnol\u00f3gica de la Mixteca, Huajuapan de Le\u00f3n 69000, Mexico"}]},{"given":"Enrique","family":"Guzm\u00e1n-Ram\u00edrez","sequence":"additional","affiliation":[{"name":"Graduate Studies Division, Universidad Tecnol\u00f3gica de la Mixteca, Huajuapan de Le\u00f3n 69000, Mexico"}]},{"given":"Iv\u00e1n","family":"Garc\u00eda-Pacheco","sequence":"additional","affiliation":[{"name":"Graduate Studies Division, Universidad Tecnol\u00f3gica de la Mixteca, Huajuapan de Le\u00f3n 69000, Mexico"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2866-1316","authenticated-orcid":false,"given":"Ignacio","family":"Arroyo-Fern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Graduate Studies Division, Universidad Tecnol\u00f3gica de la Mixteca, Huajuapan de Le\u00f3n 69000, Mexico"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Harper, L., Campbell, J., Cannon, E.K., Jung, S., Poelchau, M., Walls, R., Andorf, C., Arnaud, E., Berardini, T.Z., and Birkett, C. (2018). AgBioData consortium recommendations for sustainable genomics and genetics databases for agriculture. Database, 2018.","DOI":"10.1093\/database\/bay088"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Jehangir, B., Radhakrishnan, S., and Agarwal, R. (2023). A survey on Named Entity Recognition\u2014datasets, tools, and methodologies. Nat. Lang. Process. J., 3.","DOI":"10.1016\/j.nlp.2023.100017"},{"key":"ref_3","unstructured":"Xu, Y., Kim, M.Y., Quinn, K., Goebel, R., and Barbosa, D. (2013, January 9\u201314). Open Information Extraction with Tree Kernels. Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Atlanta, GA, USA."},{"key":"ref_4","first-page":"321","article-title":"Mapping and Cleaning Open Commonsense Knowledge Bases with Generative Translation","volume":"Volume 14265","author":"Romero","year":"2023","journal-title":"The Semantic Web\u2014ISWC 2023"},{"key":"ref_5","doi-asserted-by":"crossref","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 Trans. Neural Netw. Learn. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shi, L., Li, S., Yang, X., Qi, J., Pan, G., and Zhou, B. (2017). Semantic health knowledge graph: Semantic integration of heterogeneous medical knowledge and services. BioMed Res. Int., 2017.","DOI":"10.1155\/2017\/2858423"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4968","DOI":"10.1021\/acs.jcim.9b00683","article-title":"ROBOKOP KG and KGB: Integrated knowledge graphs from federated sources","volume":"59","author":"Bizon","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, P., Yan, J., Wang, Y., Li, S., Jiang, J., Sun, Z., Tang, B., Chang, T.H., and Wang, S. (2020). Real-world data medical knowledge graph: Construction and applications. Artif. Intell. Med., 103.","DOI":"10.1016\/j.artmed.2020.101817"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1109\/TCBB.2019.2927310","article-title":"Relation Prediction of Co-Morbid Diseases Using Knowledge Graph Completion","volume":"18","author":"Biswas","year":"2021","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Du, J., and Li, X. (2020). A knowledge graph of combined drug therapies using semantic predications from biomedical literature: Algorithm development. JMIR Med. Inform., 8.","DOI":"10.2196\/preprints.18323"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.jbi.2003.11.003","article-title":"The interaction of domain knowledge and linguistic structure in natural language processing: Interpreting hypernymic propositions in biomedical text","volume":"36","author":"Rindflesch","year":"2003","journal-title":"J. Biomed. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"W518","DOI":"10.1093\/nar\/gkt441","article-title":"PubTator: A web-based text mining tool for assisting biocuration","volume":"41","author":"Wei","year":"2013","journal-title":"Nucleic Acids Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"46004","DOI":"10.1109\/ACCESS.2019.2909069","article-title":"Diagnosis of COPD Based on a Knowledge Graph and Integrated Model","volume":"7","author":"Fang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, R., Yin, C., Yang, S., Qian, B., and Zhang, P. (2020). Marrying Medical Domain Knowledge With Deep Learning on Electronic Health Records: A Deep Visual Analytics Approach. J. Med. Internet Res., 22.","DOI":"10.2196\/preprints.20645"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, J., Gong, J., and Barnes, L. (2017, January 17\u201319). HCNN: Heterogeneous convolutional neural networks for comorbid risk prediction with electronic health records. Proceedings of the 2017 IEEE\/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), Philadelphia, PA, USA.","DOI":"10.1109\/CHASE.2017.80"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Vretinaris, A., Lei, C., Efthymiou, V., Qin, X., and \u00d6zcan, F. (2021, January 20\u201325). Medical Entity Disambiguation Using Graph Neural Networks. Proceedings of the 2021 International Conference on Management of Data, SIGMOD\/PODS \u201921, Virtual.","DOI":"10.1145\/3448016.3457328"},{"key":"ref_17","unstructured":"Crichton, G.K.O. (2019). Improving Automated Literature-Based Discovery with Neural Networks: Neural Biomedical Named Entity Recognition, Link Prediction and Discovery. [Ph.D. Thesis, University of Cambridge]."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sheikhalishahi, S., Miotto, R., Dudley, J.T., Lavelli, A., Rinaldi, F., and Osmani, V. (2019). Natural language processing of clinical notes on chronic diseases: Systematic review. JMIR Med. Inform., 7.","DOI":"10.2196\/12239"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1038\/s41551-018-0305-z","article-title":"Artificial intelligence in healthcare","volume":"2","author":"Yu","year":"2018","journal-title":"Nat. Biomed. Eng."},{"key":"ref_20","unstructured":"Yarowsky, D., Baldwin, T., Korhonen, A., Livescu, K., and Bethard, S. (2013). Effectiveness and Efficiency of Open Relation Extraction. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, WA, USA, 18\u201321 October 2013, Association for Computational Linguistics."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lin, B.Y., Chen, X., Chen, J., and Ren, X. (2019, January 3\u20137). KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1282"},{"key":"ref_22","unstructured":"Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., and Choi, Y. (August, January 28). COMET: Commonsense Transformers for Automatic Knowledge Graph Construction. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-Dur\u00e1n, A., Duman\u010di\u0107, S., and Niepert, M. (November, January 31). Learning Sequence Encoders for Temporal Knowledge Graph Completion. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-1516"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Dasgupta, S.S., Ray, S.N., and Talukdar, P. (November, January 31). HyTE: Hyperplane-based Temporally Aware Knowledge Graph Embedding. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-1225"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Han, X., Cao, S., Lv, X., Lin, Y., Liu, Z., Sun, M., and Li, J. (November, January 31). OpenKE: An Open Toolkit for Knowledge Embedding. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-2024"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Guo, S., Wang, Q., Wang, L., Wang, B., and Guo, L. (2018, January 3\u20137). Knowledge Graph Embedding with Iterative Guidance from Soft Rules. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11918"},{"key":"ref_27","first-page":"2787","article-title":"Translating Embeddings for Modeling Multi-relational Data","volume":"26","author":"Bordes","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_28","unstructured":"Yang, B., Yih, W.t., He, X., Gao, J., and Deng, L. (2015, January 7\u20139). Embedding Entities and Relations for Learning and Inference in Knowledge Bases. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Schlichtkrull, M., Kipf, T.N., Bloem, P., van den Berg, R., Titov, I., and Welling, M. (2018, January 3\u20137). Modeling Relational Data with Graph Convolutional Networks. Proceedings of the The Semantic Web, Heraklion, Crete, Greece.","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref_30","unstructured":"Vashishth, S., Sanyal, S., Nitish, V., and Talukdar, P. (2020, January 26\u201330). Composition-based Multi-Relational Graph Convolutional Networks. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Hwang, J.D., Bhagavatula, C., Le Bras, R., Da, J., Sakaguchi, K., Bosselut, A., and Choi, Y. (2021, January 2\u20139). (comet-) atomic 2020: On symbolic and neural commonsense knowledge graphs. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i7.16792"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Roberts, A., Raffel, C., and Shazeer, N. (2020). How Much Knowledge Can You Pack Into the Parameters of a Language Model?. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online, 16\u201320 November 2020, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Feng, H., and Gallinari, P. (2019). Embedding learning with triple trustiness on noisy knowledge graph. Entropy, 21.","DOI":"10.3390\/e21111083"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Vashishth, S., Jain, P., and Talukdar, P. (2018, January 23\u201327). Cesi: Canonicalizing open knowledge bases using embeddings and side information. Proceedings of the 2018 World Wide Web Conference, Lyon, France.","DOI":"10.1145\/3178876.3186030"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1145\/1409360.1409378","article-title":"Open information extraction from the web","volume":"51","author":"Etzioni","year":"2008","journal-title":"Commun. ACM"},{"key":"ref_36","unstructured":"Fader, A., Soderland, S., and Etzioni, O. (, January 27\u201331). Identifying relations for open information extraction. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Scotland, UK."},{"key":"ref_37","unstructured":"Cetto, M., Niklaus, C., Freitas, A., and Handschuh, S. (2018, January 20\u201326). Graphene: A Context-Preserving Open Information Extraction System. Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations, Santa Fe, NM, USA."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"511","DOI":"10.2307\/411934","article-title":"Dependency Theory: A Formalism and Some Observations","volume":"40","author":"Hays","year":"1964","journal-title":"Language"},{"key":"ref_39","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems\u2014NeurIPS, Long Beach, CA, USA."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., and Manning, C.D. (2015, January 17\u201321). Effective Approaches to Attention-based Neural Machine Translation. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal.","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Fang, T., Wang, W., Choi, S., Hao, S., Zhang, H., Song, Y., and He, B. (2021, January 7\u201311). Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online.","DOI":"10.18653\/v1\/2021.emnlp-main.705"},{"key":"ref_42","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. (2015, January 7\u20139). Neural Machine Translation by Jointly Learning to Align and Translate. Proceedings of the ICLR 2015: International Conference on Learning Representations 2015, San Diego, CA, USA."},{"key":"ref_43","unstructured":"Dutta, S., Gautam, T., Chakrabarti, S., and Chakraborty, T. (2021). Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems. arXiv."},{"key":"ref_44","unstructured":"Resnik, P. (1997). Selectional Preference and Sense Disambiguation. Tagging Text with Lexical Semantics: Why, What, and How?, Association for Computational Linguistics."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1093\/jos\/3.4.305","article-title":"Verbs and objects in semantic agreement: Minor differences between English and German that might suggest a major one","volume":"3","author":"Plank","year":"1984","journal-title":"J. Semant."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of Hallucination in Natural Language Generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Arroyo-Fern\u00e1ndez, I., and Meza-Ruiz, I. (2017, January 3\u20134). LIPN-IIMAS at SemEval-2017 Task 1: Subword embeddings, attention recurrent neural networks and cross word alignment for semantic textual similarity. Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), Vancouver, BC, Canada.","DOI":"10.18653\/v1\/S17-2031"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.csl.2019.01.005","article-title":"Unsupervised sentence representations as word information series: Revisiting TF\u2013IDF","volume":"56","author":"Sierra","year":"2019","journal-title":"Comput. Speech Lang."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1162\/COLI_a_00145","article-title":"Selectional preferences for semantic role classification","volume":"39","author":"Zapirain","year":"2013","journal-title":"Comput. Linguist."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Del Corro, L., and Gemulla, R. (2013, January 13\u201317). ClausIE: Clause-Based Open Information Extraction. Proceedings of the 22nd International Conference on World Wide Web, WWW \u201913, Rio de Janeiro, Brazil.","DOI":"10.1145\/2488388.2488420"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Gashteovski, K., Gemulla, R., and del Corro, L. (2017, January 9\u201311). MinIE: Minimizing Facts in Open Information Extraction. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark.","DOI":"10.18653\/v1\/D17-1278"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Bhardwaj, S., Aggarwal, S., and Mausam, M. (2019, January 3\u20137). CaRB: A Crowdsourced Benchmark for Open IE. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1651"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Lechelle, W., Gotti, F., and Langlais, P. (2019, January 1). WiRe57: A Fine-Grained Benchmark for Open Information Extraction. Proceedings of the 13th Linguistic Annotation Workshop, Florence, Italy.","DOI":"10.18653\/v1\/W19-4002"},{"key":"ref_54","unstructured":"World Health Organization (2018). Noncommunicable Diseases Country Profiles 2018, WHO."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., and McClosky, D. (2014, January 23\u201324). The Stanford CoreNLP natural language processing toolkit. Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Baltimore, MD, USA.","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref_56","unstructured":"Saha, S., Pal, H. (August, January 30). Bootstrapping for Numerical Open IE. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Vancouver, BC, Canada."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Li, X., Taheri, A., Tu, L., and Gimpel, K. (2016, January 7\u201312). Commonsense knowledge base completion. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany.","DOI":"10.18653\/v1\/P16-1137"},{"key":"ref_58","unstructured":"Dhingra, B., Zaheer, M., Balachandran, V., Neubig, G., Salakhutdinov, R., and Cohen, W.W. (2020). Differentiable reasoning over a virtual knowledge base. arXiv."},{"key":"ref_59","unstructured":"Lakew, S.M., Cettolo, M., and Federico, M. (2018, January 20\u201326). A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation. Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, NM, USA."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching word vectors with subword information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_61","first-page":"1","article-title":"Tunability: Importance of hyperparameters of machine learning algorithms","volume":"20","author":"Probst","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1093\/annonc\/mdh130","article-title":"Glycemic index, glycemic load and risk of gastric cancer","volume":"15","author":"Augustin","year":"2004","journal-title":"Ann. Oncol."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"995","DOI":"10.2337\/db07-1618","article-title":"Effect of glycemic exposure on the risk of microvascular complications in the diabetes control and complications trial\u2014revisited","volume":"57","author":"Lachin","year":"2008","journal-title":"Diabetes"},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Chen, C., Cai, F., Hu, X., Chen, W., and Chen, H. (2021). HHGN: A Hierarchical Reasoning-based Heterogeneous Graph Neural Network for Fact Verification. Inf. Process. Manag., 58.","DOI":"10.1016\/j.ipm.2021.102659"},{"key":"ref_65","unstructured":"Le, M.N. (2021). Error propagation. [Ph.D. Thesis, Vrije Universiteit Amsterdam]."},{"key":"ref_66","unstructured":"Sansford, H., Richardson, N., Maretic, H.P., and Saada, J.N. (2024). GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework. arXiv."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Ide, N., and Pustejovsky, J. (2017). FrameNet: Frame Semantic Annotation in Practice. Handbook of Linguistic Annotation, Springer.","DOI":"10.1007\/978-94-024-0881-2"},{"key":"ref_68","unstructured":"Zhang, X., Wang, Y., Yao, J., and Sun, Y. (2023). A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions. arXiv."},{"key":"ref_69","unstructured":"Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Rajani, N., Chen, Y., and Song, Y. (2022). Survey of Hallucination in Natural Language Generation. arXiv."},{"key":"ref_70","unstructured":"Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W.t., and Edunov, S. (2020, January 6\u201312). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, BC, Canada."},{"key":"ref_71","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","article-title":"Detecting hallucinations in large language models using semantic entropy","volume":"630","author":"Farquhar","year":"2024","journal-title":"Nature"},{"key":"ref_72","doi-asserted-by":"crossref","unstructured":"Filippova, K. (2020, January 16\u201320). Controlled Hallucinations:Learning to Generate Faithfully from Noisy Data. Proceedings of the Findings of EMNLP 2020, Online.","DOI":"10.18653\/v1\/2020.findings-emnlp.76"}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/6\/162\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:08Z","timestamp":1760032508000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/6\/162"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,19]]},"references-count":72,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["bdcc9060162"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9060162","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2025,6,19]]}}}