Search

Employing the properties of linguistic networks allows discovering structure and making predictions. This course seeks answers to three questions: (1) how to express the linguistic phenomena as graphs, (2) how to gain knowledge based on them, and (3) how to assess the quality of this knowledge. We will start with traditional graph-based Natural Language Processing (NLP) methods like TextRank and Markov Clustering and finish with such contemporary Machine Learning techniques as DeepWalk and Graph Convolutional Networks. As the growing interest in NLP methods urges their meaningful evaluation, we pay special attention to quality assessment and human judgements. The course has five lectures on Language Graphs, Graph Clustering, Graph Embeddings, Knowledge Graphs, and Evaluation. They elaborately go through the essential algorithms step-by-step, discuss case studies, and suggest insightful references and datasets. The target audience is undergraduate and graduate students, data analysts, and interdisciplinary researchers (but it is not limited to them). The course was held in person in August 2022 at the 33rd European Summer School in Logic, Language and Information (ESSLLI 2022) in Galway, Ireland: https://2022.esslli.eu/courses-workshops-accepted/week-1-and-2-schedule.html., {"references": ["Agirre, E., L\u00f3pez de Lacalle, O., Soroa, A.: Random Walks for Knowledge-Based Word Sense Disambiguation. Computational Linguistics. 40, 57\u201384 (2014). https://doi.org/10.1162/COLI_a_00164", "von Ahn, L., Dabbish, L.: Labeling Images with a Computer Game. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. pp. 319\u2013326. ACM, Vienna, Austria (2004). https://doi.org/10.1145/985692.985733", "Ali, M., Berrendorf, M., Hoyt, C.T., Vermue, L., Sharifzadeh, S., Tresp, V., Lehmann, J.: PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings. Journal of Machine Learning Research. 22, 1\u20136 (2021)", "Alonso, O., Rose, D.E., Stewart, B.: Crowdsourcing for Relevance Evaluation. SIGIR Forum. 42, 9\u201315 (2008). https://doi.org/10.1145/1480506.1480508", "Ardila, R., Branson, M., Davis, K., Henretty, M., Kohler, M., Meyer, J., Morais, R., Saunders, L., Tyers, F.M., Weber, G.: Common Voice: A Massively-Multilingual Speech Corpus. In: Proceedings of The 12th Language Resources and Evaluation Conference. pp. 4218\u20134222. European Language Resources Association (ELRA), Marseille, France (2020)", "Artstein, R., Poesio, M.: Inter-Coder Agreement for Computational Linguistics. Computational Linguistics. 34, 555\u2013596 (2008). https://doi.org/10.1162/coli.07-034-R2", "Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: A Nucleus for a Web of Open Data. In: The Semantic Web, 6th International Semantic Web Conference, 2nd Asian Semantic Web Conference, ISWC 2007 + ASWC 2007, Busan, Korea, November 11\u201315, 2007. Proceedings. pp. 722\u2013735. Springer Berlin Heidelberg, Berlin; Heidelberg, Germany (2007). https://doi.org/10.1007/978-3-540-76298-0_52", "Azadani, M.N., Ghadiri, N., Davoodijam, E.: Graph-based biomedical text summarization: An itemset mining and sentence clustering approach. Journal of Biomedical Informatics. 84, 42\u201358 (2018). https://doi.org/10.1016/j.jbi.2018.06.005", "Baker, C.F., Fillmore, C.J., Lowe, J.B.: The Berkeley FrameNet Project. In: Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1. pp. 86\u201390. Association for Computational Linguistics, Montr\u00e9al, QC, Canada (1998). https://doi.org/10.3115/980845.980860", "Barab\u00e1si, A.-L., Albert, R.: Emergence of Scaling in Random Networks. Science. 286, 509\u2013512 (1999). https://doi.org/10.1126/science.286.5439.509", "Bartunov, S., Kondrashkin, D., Osokin, A., Vetrov, D.: Breaking Sticks and Ambiguities with Adaptive Skip-gram. In: Proceedings of the 19th International Conference on Artificial Intelligence and Statistics. pp. 130\u2013138. PMLR, Cadiz, Spain (2016)", "Bavelas, A.: Communication Patterns in Task-Oriented Groups. The Journal of the Acoustical Society of America. 22, 725\u2013730 (1950). https://doi.org/10.1121/1.1906679", "Belkin, M., Niyogi, P.: Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Neural Computation. 15, 1373\u20131396 (2003). https://doi.org/10.1162/089976603321780317", "Biemann, C., Riedl, M.: Text: now in 2D! A framework for lexical expansion with contextual similarity. Journal of Language Modelling. 1, 55\u201395 (2013). https://doi.org/10.15398/jlm.v1i1.60", "Biemann, C.: Chinese Whispers: An Efficient Graph Clustering Algorithm and Its Application to Natural Language Processing Problems. In: Proceedings of the First Workshop on Graph Based Methods for Natural Language Processing. pp. 73\u201380. Association for Computational Linguistics, New York, NY, USA (2006). https://doi.org/10.3115/1654758.1654774", "Biemann, C.: Creating a system for lexical substitutions from scratch using crowdsourcing. Language Resources and Evaluation. 47, 97\u2013122 (2013). https://doi.org/10.1007/s10579-012-9180-5", "Biemann, C.: Structure Discovery in Natural Language. Springer Berlin Heidelberg (2012). https://doi.org/10.1007/978-3-642-25923-4", "Bird, S., Klein, E., Loper, E.: Natural Language Processing with Python. O'Reilly Media (2017)", "Blondel, V.D., Guillaume, J.-L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment. 2008, P10008 (2008). https://doi.org/10.1088/1742-5468/2008/10/P10008", "Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics. 5, 135\u2013146 (2017). https://doi.org/10.1162/tacl_a_00051", "Bonacich, P.: Power and Centrality: A Family of Measures. American Journal of Sociology. 92, 1170\u20131182 (1987). https://doi.org/10.1086/228631", "Bonnabel, S.: Stochastic Gradient Descent on Riemannian Manifolds. IEEE Transactions on Automatic Control. 58, 2217\u20132229 (2013). https://doi.org/10.1109/TAC.2013.2254619", "Bordea, G., Lefever, E., Buitelaar, P.: SemEval-2016 Task 13: Taxonomy Extraction Evaluation (TExEval-2). In: Proceedings of the 10th International Workshop on Semantic Evaluation. pp. 1081\u20131091. Association for Computational Linguistics, San Diego, CA, USA (2016). https://doi.org/10.18653/v1/S16-1168", "Bordes, A., Chopra, S., Weston, J.: Question Answering with Subgraph Embeddings. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. pp. 615\u2013620. Association for Computational Linguistics, Doha, Qatar (2014). https://doi.org/10.3115/v1/D14-1067", "Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating Embeddings for Modeling Multi-relational Data. In: Advances in Neural Information Processing Systems 26. pp. 2787\u20132795. Curran Associates, Inc., Lake Tahoe, NV, USA (2013)", "Boudin, F.: A Comparison of Centrality Measures for Graph-Based Keyphrase Extraction. In: Proceedings of the Sixth International Joint Conference on Natural Language Processing. pp. 834\u2013838. Asian Federation of Natural Language Processing, Nagoya, Japan (2013)", "Brandes, U.: On variants of shortest-path betweenness centrality and their generic computation. Social Networks. 30, 136\u2013145 (2008). https://doi.org/10.1016/j.socnet.2007.11.001", "Brin, S., Page, L.: The anatomy of a large-scale hypertextual Web search engine. Computer Networks and ISDN Systems. 30, 107\u2013117 (1998). https://doi.org/10.1016/S0169-7552(98)00110-X", "Brody, S., Alon, U., Yahav, E.: How Attentive are Graph Attention Networks? In: 10th International Conference on Learning Representations. OpenReview.net, Virtual (2022)", "Buckley, C., Voorhees, E.M.: Evaluating Evaluation Measure Stability. In: Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 33\u201340. Association for Computing Machinery, Athens, Greece (2000). https://doi.org/10.1145/345508.345543", "Cai, H., Zheng, V.W., Chen-Chuan Chang, K.: A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications. IEEE Transactions on Knowledge and Data Engineering. 30, 1616\u20131637 (2018). https://doi.org/10.1109/TKDE.2018.2807452", "Callison-Burch, C.: Fast, Cheap, and Creative: Evaluating Translation Quality Using Amazon's Mechanical Turk. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. pp. 286\u2013295. Association for Computational Linguistics; Asian Federation of Natural Language Processing, Singapore (2009). https://doi.org/10.3115/1699510.1699548", "Camacho-Collados, J., Delli Bovi, C., Espinosa-Anke, L., Oramas, S., Pasini, T., Santus, E., Shwartz, V., Navigli, R., Saggion, H.: SemEval-2018 Task 9: Hypernym Discovery. In: Proceedings of The 12th International Workshop on Semantic Evaluation. pp. 712\u2013724. Association for Computational Linguistics, New Orleans, LA, USA (2018). https://doi.org/10.18653/v1/S18-1115", "Chang, J., Boyd-Graber, J., Gerrish, S., Wang, C., Blei, D.M.: Reading Tea Leaves: How Humans Interpret Topic Models. In: Advances in Neural Information Processing Systems 22. pp. 288\u2013296. Curran Associates, Inc., Vancouver, BC, Canada (2009)", "Chapelle, O., Metlzer, D., Zhang, Y., Grinspan, P.: Expected Reciprocal Rank for Graded Relevance. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management. pp. 621\u2013630. Association for Computing Machinery, Hong Kong, China (2009). https://doi.org/10.1145/1645953.1646033", "Chen, D., Lin, Y., Li, W., Li, P., Zhou, J., Sun, X.: Measuring and Relieving the Over-Smoothing Problem for Graph Neural Networks from the Topological View. Proceedings of the AAAI Conference on Artificial Intelligence. 34, 3438\u20133445 (2020). https://doi.org/10.1609/aaai.v34i04.5747", "Chicco, D., Jurman, G.: The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics. 21, 6 (2020). https://doi.org/10.1186/s12864-019-6413-7", "Cimiano, P., Chiarcos, C., McCrae, J.P., Gracia, J.: Linguistic Linked Data: Representation, Generation and Applications. Springer International Publishing (2020). https://doi.org/10.1007/978-3-030-30225-2", "Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms. MIT Press (2022)", "Cs\u00e1rdi, G., Nepusz, T.: The igraph software package for complex network research. InterJournal Complex Systems. 1695, 1\u20139 (2006)", "Dacrema, M.F., Cremonesi, P., Jannach, D.: Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches. In: Proceedings of the 13th ACM Conference on Recommender Systems. pp. 101\u2013109. Association for Computing Machinery, Copenhagen, Denmark (2019). https://doi.org/10.1145/3298689.3347058", "Davis, J., Goadrich, M.: The Relationship between Precision-Recall and ROC Curves. In: Proceedings of the 23rd International Conference on Machine Learning. pp. 233\u2013240. Association for Computing Machinery, Pittsburgh, PA, USA (2006). https://doi.org/10.1145/1143844.1143874", "Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, MN, USA (2019). https://doi.org/10.18653/v1/N19-1423", "Dijkstra, E.W.: A note on two problems in connexion with graphs. Numerische Mathematik. 1, 269\u2013271 (1959). https://doi.org/10.1007/BF01386390", "Dong, X., Gabrilovich, E., Heitz, G., Horn, W., Lao, N., Murphy, K., Strohmann, T., Sun, S., Zhang, W.: Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 601\u2013610. Association for Computing Machinery, New York, NY, USA (2014). https://doi.org/10.1145/2623330.2623623", "van Dongen, S.: Graph Clustering by Flow Simulation, (2000)", "Dorogovtsev, S.N., Mendes, J.F.F.: Language as an evolving word web. Proceedings of the Royal Society of London B: Biological Sciences. 268, 2603\u20132606 (2001). https://doi.org/10.1098/rspb.2001.1824", "Dorogovtsev, S.N., Mendes, J.F.F.: The Nature of Complex Networks. Oxford University Press, Oxford, UK (2022)", "Dorow, B., Widdows, D.: Discovering Corpus-Specific Word Senses. In: Proceedings of the Tenth Conference on European Chapter of the Association for Computational Linguistics - Volume 2. pp. 79\u201382. Association for Computational Linguistics, Budapest, Hungary (2003). https://doi.org/10.3115/1067737.1067753", "Dror, R., Baumer, G., Shlomov, S., Reichart, R.: The Hitchhiker's Guide to Testing Statistical Significance in Natural Language Processing. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 1383\u20131392. Association for Computational Linguistics, Melbourne, VIC, Australia (2018). https://doi.org/10.18653/v1/P18-1128", "Estell\u00e9s-Arolas, E., Gonz\u00e1lez-Ladr\u00f3n-de-Guevara, F.: Towards an integrated crowdsourcing definition. Journal of Information Science. 38, 189\u2013200 (2012). https://doi.org/10.1177/0165551512437638", "Faralli, S., Panchenko, A., Biemann, C., Ponzetto, S.P.: Linked Disambiguated Distributional Semantic Networks. In: The Semantic Web \u2013 ISWC 2016, 15th International Semantic Web Conference, Kobe, Japan, October 17\u201321, 2016, Proceedings, Part II. pp. 56\u201364. Springer International Publishing, Cham, Switzerland (2016). https://doi.org/10.1007/978-3-319-46547-0_7", "Faruqui, M., Dodge, J., Jauhar, S.K., Dyer, C., Hovy, E., Smith, N.A.: Retrofitting Word Vectors to Semantic Lexicons. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 1606\u20131615. Association for Computational Linguistics, Denver, CO, USA (2015). https://doi.org/10.3115/v1/N15-1184", "Fellbaum, C.: WordNet: An Electronic Database. MIT Press, Massachusetts, MA, USA (1998). https://doi.org/10.7551/mitpress/7287.001.0001", "Fey, M., Lenssen, J.E.: Fast Graph Representation Learning with PyTorch Geometric. In: ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds, New Orleans, LA, USA (2019)", "Fillmore, C.J.: Frame Semantics. In: Linguistics in the Morning Calm. pp. 111\u2013137. Hanshin Publishing Co., Seoul, South Korea (1982)", "Florescu, C., Caragea, C.: PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 1105\u20131115. Association for Computational Linguistics, Vancouver, BC, Canada (2017). https://doi.org/10.18653/v1/P17-1102", "Fortunato, S.: Community detection in graphs. Physics Reports. 486, 75\u2013174 (2010). https://doi.org/10.1016/j.physrep.2009.11.002", "Fowlkes, E.B., Mallows, C.L.: A Method for Comparing Two Hierarchical Clusterings. Journal of the American Statistical Association. 78, 553\u2013569 (1983). https://doi.org/10.1080/01621459.1983.10478008", "Freeman, L.C.: A Set of Measures of Centrality Based on Betweenness. Sociometry. 40, 35\u201341 (1977). https://doi.org/10.2307/3033543", "Frey, B.J., Dueck, D.: Clustering by Passing Messages Between Data Points. Science. 315, 972\u2013976 (2007). https://doi.org/10.1126/science.1136800", "Fu, R., Guo, J., Qin, B., Che, W., Wang, H., Liu, T.: Learning Semantic Hierarchies via Word Embeddings. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers. pp. 1199\u20131209. Association for Computational Linguistics, Baltimore, MD, USA (2014). https://doi.org/10.3115/v1/P14-1113", "Gallardo, P.F.: Google's secret and Linear Algebra. EMS Newsletter. 63, 10\u201315 (2007)", "Goldhahn, D., Eckart, T., Quasthoff, U.: Building Large Monolingual Dictionaries at the Leipzig Corpora Collection: From 100 to 200 Languages. In: Proceedings of the Eight International Conference on Language Resources and Evaluation. pp. 759\u2013765. European Language Resources Association (ELRA), Istanbul, Turkey (2012)", "Gonzalez, J.E., Xin, R.S., Dave, A., Crankshaw, D., Franklin, M.J., Stoica, I.: GraphX: Graph Processing in a Distributed Dataflow Framework. In: 11th USENIX Symposium on Operating Systems Design and Implementation. pp. 599\u2013613. USENIX Association, Broomfield, CO, USA (2014)", "Good, B.H., de Montjoye, Y.-A., Clauset, A.: Performance of modularity maximization in practical contexts. Physical Review E. 81, 046106 (2010). https://doi.org/10.1103/PhysRevE.81.046106", "Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge, MA, USA (2016)", "Gorodkin, J.: Comparing two K-category assignments by a K-category correlation coefficient. Computational Biology and Chemistry. 28, 367\u2013374 (2004). https://doi.org/10.1016/j.compbiolchem.2004.09.006", "Goyal, P., Ferrara, E.: Graph embedding techniques, applications, and performance: A survey. Knowledge-Based Systems. 151, 78\u201394 (2018). https://doi.org/10.1016/j.knosys.2018.03.022", "Grover, A., Leskovec, J.: node2vec: Scalable Feature Learning for Networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 855\u2013864. ACM, San Francisco, CA, USA (2016). https://doi.org/10.1145/2939672.2939754", "G\u00f6sgens, M., Tikhonov, A., Prokhorenkova, L.: Systematic Analysis of Cluster Similarity Indices: How to Validate Validation Measures. In: Proceedings of the 38th International Conference on Machine Learning. pp. 3799\u20133808. PMLR, Online (2021)", "G\u00f6sgens, M., Zhiyanov, A., Tikhonov, A., Prokhorenkova, L.: Good Classification Measures and How to Find Them. In: Advances in Neural Information Processing Systems 34. pp. 17136\u201317147. Curran Associates, Inc., Online (2021)", "Hagberg, A.A., Schult, D.A., Swart, P.J.: Exploring Network Structure, Dynamics, and Function using NetworkX. In: Proceedings of the 7th Python in Science Conference. pp. 11\u201315, Pasadena, CA, USA (2008)", "Hamilton, W.L., Ying, R., Leskovec, J.: Inductive Representation Learning on Large Graphs. In: Advances in Neural Information Processing Systems 30. pp. 1024\u20131034. Curran Associates, Inc., Vancouver, BC, Canada (2017)", "Han, X., Cao, S., Lv, X., Lin, Y., Liu, Z., Sun, M., Li, J.: OpenKE: An Open Toolkit for Knowledge Embedding. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. pp. 139\u2013144. Association for Computational Linguistics, Brussels, Belgium (2018). https://doi.org/10.18653/v1/D18-2024", "Hansen, P.C.: The truncatedSVD as a method for regularization. BIT Numerical Mathematics. 27, 534\u2013553 (1987). https://doi.org/10.1007/BF01937276", "Hartigan, J.A., Wong, M.A.: Algorithm AS 136: A K-Means Clustering Algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics). 28, 100\u2013108 (1979). https://doi.org/10.2307/2346830", "Hearst, M.A.: Automatic Acquisition of Hyponyms from Large Text Corpora. In: Proceedings of the 14th Conference on Computational Linguistics - Volume 2. pp. 539\u2013545. Association for Computational Linguistics, Nantes, France (1992). https://doi.org/10.3115/992133.992154", "Heo, Y.-J., Kim, E.-S., Choi, W.S., Zhang, B.-T.: Hypergraph Transformer: Weakly-Supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 373\u2013390. Association for Computational Linguistics, Dublin, Ireland (2022). https://doi.org/10.18653/v1/2022.acl-long.29", "Hitzler, P.: A Review of the Semantic Web Field. Communications of the ACM. 64, 76\u201383 (2021). https://doi.org/10.1145/3397512", "Hochreiter, S., Schmidhuber, J.: Long Short-Term Memory. Neural Computation. 9, 1735\u20131780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735", "Hogan, A., Blomqvist, E., Cochez, M., D'amato, C., Melo, G.D., Gutierrez, C., Kirrane, S., Gayo, J.E.L., Navigli, R., Neumaier, S., Ngomo, A.-C.N., Polleres, A., Rashid, S.M., Rula, A., Schmelzeisen, L., Sequeda, J., Staab, S., Zimmermann, A.: Knowledge Graphs. ACM Computing Surveys. 54, 1\u201337 (2021). https://doi.org/10.1145/3447772", "Hope, D., Keller, B.: MaxMax: A Graph-Based Soft Clustering Algorithm Applied to Word Sense Induction. In: Computational Linguistics and Intelligent Text Processing, 14th International Conference, CICLing 2013, Samos, Greece, March 24-30, 2013, Proceedings, Part I. pp. 368\u2013381. Springer Berlin Heidelberg, Berlin; Heidelberg, Germany (2013). https://doi.org/10.1007/978-3

The object of research is the use of multi-agent systems for text data mining. The need for this study arose with a tendency to increase the amount of textual information gene rated in the world. Accordingly, it is necessary to develop and research methods of its processing, as well as ways to use the results of this processing, because the methods can’t exist in isolation from practice. At the same time, there is a development of multi-agent sys-tems (MAS), where agents are endowed with some kind of intelligence, these systems can be easily scaled. The use of MAS for text analysis is a promising area. The following methods of text data analysis were used in this study: TF-IDF and RAKE methods, Word2Vec neural network models, and TextRank. The algorithms were compared for their work and the results were compared. The corpus of documents (10–12 texts, 5732–12331 words) from the subject areas of physics and biology were used as a test set. According to the results of the study, one method was chosen, on the basis of which the MAS was built to solve the problem. Additionally, Schulze methods (with one and several winners) were used for voting. With the received system additional researches concerning accuracy and speed of work, and also – influence are carried out system parameters for its operation. It has been found that TF-IDF-based analysis is useful for finding terms in documents with a weak context. The resulting system shows an accuracy of 75 % (3 of the 4 words proposed by the system are terms). The maxi-mum operating time on test cases is 2–3 seconds, which is achieved through the use of parallel calculations and modification of the Schulze method. The results obtained in this paper are heuristic (ontology is a rather vague concept) and require additional elaboration by experts in the relevant fields. However, the results are positive within this experiment.

As the amount of published geoscience literature grows, reading and summarizing texts of large collections has become a challenging task. Publication keywords can be considered basic components of knowledge structure representations and have been used to reveal knowledge concerning research domains. In contrast to data used in other research domains, the works on textual geoscience data that entail keyword extraction are limited. In this paper, we propose an unsupervised algorithm, the graph‐based keyword extractor with error‐feedback propagation (GKEEP), that enhances graph‐based keyword extraction approaches by using an error‐feedback mechanism similar to the concept of backpropagation. The proposed approach comprises the following steps. A preprocessed document is used as the input of the proposed model and is represented as a weighted undirected graph, where the vertices represent words and the edges represent the cooccurrence relationship between the words constrained by a window size. Subsequently, its nodes are ranked by their importance scores calculated by a graph‐based ranking algorithm. Consequently, all the words have their own scores, and they are used to compute the scores of keyword candidates. Subsequently, the Word2Vec method is applied to recalculate the scores of keyword candidates and rank the keyword candidates to select the final keyword. It also utilizes error feedback to boost the rankings of the most salient terms that would otherwise be deemed less important. With empirical experiments on two real data sets (including our newly built data set), the proposed GKEEP model outperforms state‐of‐the‐art unsupervised models and the existing graph‐based ranking models. The proposed method can effectively reflect intrinsic keyword semantics and interrelationships.

Es evidente que actualmente el Text Mining es considerado como un ámbito de gran importancia y progresión. En este trabajo, comenzando con la descripción de su composición y relación con otros campos, se analizan sus principios básicos, de preprocesamiento, representación y aplicación, así como las técnicas características para su implementación. De igual forma, con el objetivo de ilustrar algunos de los desarrollos teóricos expuestos, se plantea, como caso práctico, un problema de clasificación múltiple sobre temáticas de libros a través de su sinopsis. No obstante, para poder alcanzar dicho propósito, previamente, resultan esenciales las etapas de tratamiento y resumen de información. Finalmente, para su confirmación, tras la construcción y evaluación de los modelos correspondientes, también resultó de interés llevar a cabo una identificación de temáticas, comprobando de esta forma si realmente es posible captar los conceptos y relaciones existentes entre los géneros preestablecidos. Universidad de Sevilla. Doble Grado en Matemáticas y Estadística

The object of research is the use of multi-agent systems for text data mining. The need for this study arose with a tendency to increase the amount of textual information generated in the world. Accordingly, it is necessary to develop and research methods of its processing, as well as ways to use the results of this processing, because the methods can’t exist in isolation from practice. At the same time, there is a development of multi-agent systems (MAS), where agents are endowed with some kind of intelligence, these systems can be easily scaled. The use of MAS for text analysis is a promising area.The following methods of text data analysis were used in this study: TF-IDF and RAKE methods, Word2Vec neural network models, and TextRank. The algorithms were compared for their work and the results were compared. The corpus of documents (10–12 texts, 5732–12331 words) from the subject areas of physics and biology were used as a test set. According to the results of the study, one method was chosen, on the basis of which the MAS was built to solve the problem. Additionally, Schulze methods (with one and several winners) were used for voting. With the received system additional researches concerning accuracy and speed of work, and also – influence are carried out system parameters for its operation.It has been found that TF-IDF-based analysis is useful for finding terms in documents with a weak context. The resulting system shows an accuracy of 75 % (3 of the 4 words proposed by the system are terms). The maximum operating time on test cases is 2–3 seconds, which is achieved through the use of parallel calculations and modification of the Schulze method. The results obtained in this paper are heuristic (ontology is a rather vague concept) and require additional elaboration by experts in the relevant fields. However, the results are positive within this experiment, Объектом исследования является использование мультиагентных систем для анализа текстовых данных. Необходимость данного исследования возникла с тенденцией к увеличению количества текстовой информации, генерируемой в мире. Соответственно, нужно разрабатывать и исследовать методы ее обработки, а также – способы использования результатов данной обработки, ведь методы не могут существовать в отрыве от практики. Одновременно с этим происходит развитие мультиагентных систем (МАС), в которых агенты наделены некоторого рода интеллектом, данные системы могут легко масштабироваться. Использование МАС для анализа текстов является перспективным направлением.В данном исследовании были использованы следующие методы анализа текстовых данных: методы TF-IDF и RAKE, модели нейронных сетей Word2Vec, а также TextRank. Проводилось сравнение алгоритмов на предмет их работы и сравнение результатов. В качестве тестового набора было использовано корпуса документов (10–12 текстов, 5732–12331 слов) из предметных областей физика и биология. По результатам исследования был выбран один метод, на основе которого была построена МАС для решения поставленной задачи. Дополнительно использованы методы Шульце (с одним и несколькими победителями) для голосования. С полученной системой проведены дополнительные исследования точности и скорости работы, а также – влияния параметров системы на ее работу.Обнаружено, что для поиска терминов в документах со слабым контекстом целесообразным является анализ на основе TF-IDF. Полученная система показывает точность в пределах 75 % (3 из 4 предложенных системой слов являются терминами). Время работы на тестовых корпусах – 2–3 секунды, что достигается с помощью использования параллельных вычислений и модификации метода Шульце. Полученные в данной работе результаты являются эвристическими (онтология является достаточно нечетким понятием) и требуют дополнительной проработки экспертами по соответствующим направлениям. Однако результаты положительны в рамках данного эксперимента., Об’єктом дослідження є використання мультиагентних систем для аналізу текстових даних. Необхідність даного дослідження виникла з тенденцією до збільшення кількості текстової інформації, що генерується у світі. Відповідно, потрібно розробляти та досліджувати методи її обробки, а також – способи використання результатів даної обробки, адже методи не можуть існувати у відриві від практики. Одночасно з цим відбувається розвиток мультиагентних систем (МАС), в яких агенти наділені деякого роду інтелектом, дані системи можуть легко масштабуватися. Використання МАС для аналізу текстів є перспективним напрямком.В даному дослідженні було використані наступні методи аналізу текстових даних: методи TF-IDF та RAKE, моделі нейронних мереж Word2Vec, а також TextRank. Проводилося порівняння алгоритмів на предмет їх роботи та порівняння результатів. У ролі тестового набору було використано корпуси документів (10–12 текстів, 5732–12331 слів) з предметних областей фізика та біологія. За результатами дослідження було обрано один метод, на основі якого було побудовано МАС для вирішення поставленої задачі. Додатково використано методи Шульце (з одним та декількома переможцями) для голосування. З отриманою системою проведені додаткові дослідження щодо точності та швидкості роботи, а також – впливу параметрів системи на її роботу.Виявлено, що для пошуку термінів в документах зі слабким контекстом доцільним є аналіз на основі TF-IDF. Отримана система показує точність в межах 75 % (3 з 4 запропонованих системою слів є термінами). Максимальний час роботи на тестових корпусах – 2–3 секунди, що досягається за допомогою використання паралельних обчислень та модифікації методу Шульце. Отримані в даній роботі результати є евристичними (онтологія є досить нечітким поняттям) та потребують додаткового опрацювання експертами з відповідних напрямів. Проте результати є позитивними в межах даного експерименту.

Jacob is a voice chatbot that use Wit.ai to get the context of the question and give an answer based on that context. However, Jacob has no variation in answer and could not recognize the context well if it has not been learned previously by the Wit.ai. Thus, this paper proposes two features of artificial intelligence (AI) built as a web service: the paraphrase of answers using the Stacked Residual LSTM model and the question summarization using Cosine Similarity with pre-trained Word2Vec and TextRank algorithm. These two features are novel designs that are tailored to Jacob, this AI module is called Cleveree. The evaluation of Cleveree is carried out using the technology acceptance model (TAM) method and interview with Jacob admins. The results show that 79.17% of respondents strongly agree that both features are useful and 72.57% of respondents strongly agree that both features are easy to use.

Railways have developed rapidly in China for several decades. The hardware of railways has already reached the world's leading level, but the level of service of these railways still has room for improvement. The railway management department receives a large number of passenger complaints every year and records them in text, which needs to be classified and analyzed. The text of railway complaints includes characteristics spanning wide business coverage, various events, serious colloquialisms, interference and useless information. When using the direct classification via traditional text categorization, the classification accuracy is low. The key to the automatic classification of such text lies in an eigenvalue extraction. The more accurate the eigenvalue extraction, the higher the accuracy of text classification. In this paper, the TF-IDF algorithm, TextRank algorithm and Word2vec algorithm are selected to extract text eigenvalues, and a railway complaint text classification method is constructed with a naive Bayesian classifier. The three types of eigenvalue extraction algorithms are compared. The TF-IDF algorithm, based on eigenvalue extraction, achieves the highest automatic text classification accuracy.