Sistem Tanya Jawab menggunakan Knowledge Graph mengenai Sistem Tata Surya
Abstract
Abstrak - Manfaat dari Knowledge Graph (KG) bisa kita amati langsung, seperti optimalisasi search engine query Google, yang mempermudah dalam mencari sesuatu di internet. Diatas KG bisa juga dibangun sebuah Question Answering System (QA). Penelitian ini menggunakan artikel-artikel mengenai sistem tata surya dari halaman web NASA. Dengan menggunakan NLTK, artikel-artikel yang didapatkan dari halaman web NASA dipecah ke dalam bentuk triple. Triple tersebut kemudian diubah ke dalam bentuk Knowledge Graph yang disimpan di dalam Neo4j, kemudian dibangun QA System diatasnya. Proses validasi hasil sistem melibatkan ahli di bidang Astronomi. Hasil dari sistem ini adalah sistem yang menjawab query pertanyaan mengenai sistem tata surya. Performansi sistem diukur menggunakan akurasi, precision, recall, f1 score, dan mean reciprocal rank, yang mana didapatkan Akurasi = 0.78, Precision = 0.5, Recall = 1, F1 Score = 0.67, dan MRR = 0.2112955621.
Kata kunci - Knowledge Graph, Question Answering system, NASA, triple, sistem tata surya.
References
Philipp Christmann, Rishiraj Saha Roy, Abdalghani Abujabal, Jyotsna Singh, and Gerhard Weikum. 2019. Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM '19). Association for Computing Machinery, New York, NY, USA, 7293738. DOI:https://doi.org/10.1145/3357384.3358016
Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, and Gerhard Weikum. 2018. Never-ending learning for open-domain question answering over knowledge bases. In WWW.
Hannah Bast and Elmar Haussmann. 2015. More accurate question answering on Freebase. In CIKM.
Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic parsing on Freebase from question-answer pairs. In EMNLP.
Dennis Diefenbach, Pedro Henrique Migliatti, Omar Qawasmeh, Vincent Lully, Kamal Singh, and Pierre Maret. 2019. QAnswer: A Question Answering prototype bridging the gap between a considerable part of the LOD cloud and end-users. In WWW.
Xiao Huang, Jingyuan Zhang, Dingcheng Li, and Ping Li. 2019. Knowledge graph embedding based question answering. In WSDM.
Thomas Pellissier Tanon, Marcos Dias de Assuncao, Eddy Caron, and Fabian M Suchanek. 2018. Demoing Platypus 3 A multilingual question answering platform for Wikidata. In ESWC.
Christina Unger, Lorenz Bühmann, Jens Lehmann, Axel-Cyrille Ngonga Ngomo, Daniel Gerber, and Philipp Cimiano. 2012. Template-based question answering over RDF data. In WWW.
Mohamed Yahya, Klaus Berberich, Shady Elbassuoni, and Gerhard Weikum. 2013. Robust question answering over the web of linked data. In CIKM.
Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, and Gerhard Weikum. 2017. QUINT: Interpretable Question Answering over Knowledge Bases. In EMNLP. [11] Chowdhury, Sudip. (2019). Knowledge Graph: The Perfect Complement to Machine Learning. [Online] available at: https://towardsdatascience.com/knowledge-graphbb78055a7884 [12] Paulheim, H. (2017). Knowledge graph refinement: A survey of approaches and evaluation methods. Semantic Web, 8(3):4893508. [13] Nigam, V. V., Paul, S., Agrawal, A. P., and Bansal, R. (2020). A review paper on the application of knowledge graph on various service providing platforms. In 2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence), pages 7163720. IEEE. [14] Simone, S. (2020). Using knowledge graphs and search for decision intelligence. KMWorld. [15] Hannah Bast and Elmar Haussmann. 2015. More accurate question answering on freebase. In CIKM. [16] Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic parsing on Freebase from question-answer pairs. In EMNLP. [17] Siva Reddy, Mirella Lapata, and Mark Steedman. 2014. Large-scale semantic parsing without question-answer pairs. TACL. [18] Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. 2015. Semantic parsing via staged query graph generation: Question answering with knowledge base. In ACL. [19] Swalin, Alvira. (2018). Building a QuestionAnswering System from Scratch4 Part 1. [Online] available at: https://towardsdatascience.com/building-aquestion-answering-system-part-1-9388aadff507 [20] Gao, J., Li, X., Xu, Y.E., Sisman, B., Dong, X.L., Yang, J.: Efficient knowledge graph accuracy evaluation. Technical Report (2019). https://users.cs.duke.edu/∼jygao/KG_eval_vldb_f ull.pdf [21] Loper, E., & Bird, S. (2002). Nltk: The natural language toolkit. arXiv preprint cs/0205028. [22] Harris, M. (2023, June 27). Sistem Tata Surya: Definisi, Teori, dan Sistem Penyusunnya. Gramedia Literasi. https://www.gramedia.com/literasi/sistem-tatasurya/ [23] Natasha Noy, Yuqing Gao, Anshu Jain, Anant Narayanan, Alan Patterson, and Jamie Taylor. 2019. Industry-scale knowledge graphs: lessons and challenges. Commun. ACM 62, 8 (August 2019), 36343. https://doi.org/10.1145/3331166 [24] Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia D’amato, Gerard De Melo, Claudio Gutierrez, Sabrina Kirrane, José Emilio Labra Gayo, Roberto Navigli, Sebastian Neumaier, AxelCyrille Ngonga Ngomo, Axel Polleres, Sabbir M. Rashid, Anisa Rula, Lukas Schmelzeisen, Juan Sequeda, Steffen Staab, and Antoine Zimmermann. 2021. Knowledge Graphs. ACM Comput. Surv. 54, 4, Article 71 (May 2022), 37 pages. https://doi.org/10.1145/3447772 [25] What is spaCy? | Domino Data Lab. (n.d.). https://domino.ai/data-science-dictionary/spacy [26] Sun: Facts - NASA Science. (n.d.). https://science.nasa.gov/sun/facts/ [27] Mercury: Facts - NASA Science. (n.d.). https://science.nasa.gov/mercury/facts/ [28] Venus: Facts - NASA Science. (n.d.). https://science.nasa.gov/venus/venus-facts/ [29] Facts About Earth - NASA Science. (n.d.). https://science.nasa.gov/earth/facts [30] Mars: Facts - NASA Science. (n.d.). https://science.nasa.gov/mars/facts/ [31] Jupiter: Facts - NASA Science. (n.d.). https://science.nasa.gov/jupiter/jupiter-facts/ [32] Saturn: Facts - NASA Science. (n.d.). https://science.nasa.gov/saturn/facts/ [33] Uranus: Facts - NASA Science. (n.d.). https://science.nasa.gov/uranus/facts/ [34] Neptune: Facts - NASA Science. (n.d.). https://science.nasa.gov/neptune/facts/ [35] Moon Facts - NASA Science. (n.d.). https://science.nasa.gov/moon/facts/ [36] Solar System: Facts - NASA Science. (n.d.). https://science.nasa.gov/solar-system/solarsystem-facts/ [37] Bhattbhavesh. (n.d.-b). neo4j-tutorials/2-movieq-and-a-neo4j-notebook.ipynb at main · bhattbhavesh91/neo4j-tutorials. GitHub. https://github.com/bhattbhavesh91/neo4jtutorials/blob/main/2-movie-q-and-a-neo4jnotebook.ipynb [38] Barney, N. (2023, March 10). named entity recognition (NER). WhatIs. https://www.techtarget.com/whatis/definition/na med-entity-recognition-NER
