{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:30:02Z","timestamp":1777573802375,"version":"3.51.4"},"reference-count":71,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2017,7,17]],"date-time":"2017-07-17T00:00:00Z","timestamp":1500249600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Argument &amp; Computation"],"published-print":{"date-parts":[[2018,1,31]]},"abstract":"<jats:p>\n                    Argumentation mining is an advanced form of human language understanding by the machine. This is a challenging task for a machine. When sufficient explicit discourse markers are present in the language utterances, the argumentation can be interpreted by the machine with an acceptable degree of accuracy. However, in many real settings, the mining task is difficult due to the lack or ambiguity of the discourse markers, and the fact that a substantial amount of knowledge needed for the correct recognition of the argumentation, its composing elements and their relationships is not explicitly present in the text, but makes up the background knowledge that humans possess when interpreting language. In this article 1\n                    <jats:sup>1<\/jats:sup>\n                    The article is the written version of a keynote lecture given at COMMA 2016, the 6th International Conference on Computational Models of Argument, on September 13, 2016 at Potsdam University, Germany. we focus on how the machine can automatically acquire the needed common sense and world knowledge. As very few research has been done in this respect, many of the ideas proposed in this article are tentative, but start being researched.\n                  <\/jats:p>\n                  <jats:p>We give an overview of the latest methods for human language understanding that map language to a formal knowledge representation that facilitates other tasks (for instance, a representation that is used to visualize the argumentation or that is easily shared in a decision or argumentation support system). Most current systems are trained on texts that are manually annotated. Then we go deeper into the new field of representation learning that nowadays is very much studied in computational linguistics. This field investigates methods for representing language as statistical concepts or as vectors, allowing straightforward methods of compositionality. The methods often use deep learning and its underlying neural network technologies to learn concepts from large text collections in an unsupervised way (i.e., without the need for manual annotations). We show how these methods can help the argumentation mining process, but also demonstrate that these methods need further research to automatically acquire the necessary background knowledge and more specifically common sense and world knowledge. We propose a number of ways to improve the learning of common sense and world knowledge by exploiting textual and visual data, and touch upon how we can integrate the learned knowledge in the argumentation mining process.<\/jats:p>","DOI":"10.3233\/aac-170025","type":"journal-article","created":{"date-parts":[[2017,7,18]],"date-time":"2017-07-18T10:42:34Z","timestamp":1500374554000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":22,"title":["Argumentation mining: How can a machine acquire common sense and world knowledge?"],"prefix":"10.1177","volume":"9","author":[{"given":"Marie-Francine","family":"Moens","sequence":"first","affiliation":[{"name":"Department of Computer Science, KU Leuven, Belgium. E-mail:\u00a0"}]}],"member":"179","published-online":{"date-parts":[[2017,7,17]]},"reference":[{"key":"ref001","unstructured":"P.\u00a0Agrawal, A.\u00a0Nair, P.\u00a0Abbeel, J.\u00a0Malik and S.\u00a0Levine, Learning to poke by poking: Experiential Learning of intuitive physics,\n                      Advances in Neural Information Processing Systems\n                      (2016)."},{"key":"ref002","first-page":"1137","volume":"3","author":"Bengio Y.","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref003","first-page":"993","volume":"3","author":"Blei D.M.","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref004","doi-asserted-by":"crossref","unstructured":"S.R.\u00a0Bowman, J.\u00a0Gauthier, A.\u00a0Rastogi, R.\u00a0Gupta, C.D.\u00a0Manning and C.\u00a0Potts, A fast unified model for parsing and sentence understanding, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL, 2016, pp.\u00a01466\u20131477.","DOI":"10.18653\/v1\/P16-1139"},{"key":"ref005","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4135"},{"key":"ref006","doi-asserted-by":"crossref","unstructured":"T.\u00a0Brychc\u00edn, Latent tree language model, in: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP), ACL, 2016, pp.\u00a0436\u2013446.","DOI":"10.18653\/v1\/D16-1042"},{"key":"ref007","doi-asserted-by":"publisher","DOI":"10.3233\/AAC-160005"},{"key":"ref008","doi-asserted-by":"crossref","unstructured":"H.\u00a0Bunt, J.\u00a0Bos and S.\u00a0Pulman, Introduction: Computing meaning: Annotation, representation, and inference, in: Computing Meaning, H.\u00a0Bunt, J.\u00a0Bos and S.\u00a0Pulman, eds, Text, Speech and Language Technology, Vol. 47, Springer, 2014, pp.\u00a01\u20139.","DOI":"10.1007\/978-94-007-7284-7_1"},{"key":"ref009","unstructured":"E.\u00a0Cabrio and S.\u00a0Villata, Detecting bipolar semantic relations among natural language arguments with textual entailment: A study, in: Proceedings of the Joint Symposium on Semantic Processing (JSSP-2013), 2013."},{"key":"ref010","unstructured":"E.\u00a0Cabrio, S.\u00a0Villata and A.Z.\u00a0Wyner\u00a0(eds), Proceedings of the Workshop on Frontiers and Connections Between Argumentation Theory and Natural Language Processing, CEUR Workshop Proceedings, Vol.\u00a01341, CEUR-WS.org, 2015."},{"key":"ref011","unstructured":"C.\u00a0Cardie, N.\u00a0Green, I.\u00a0Gurevych, G.\u00a0Hirst, D.\u00a0Litman, S.\u00a0Muresan, G.\u00a0Petasis, M.\u00a0Stede, M.\u00a0Walker and J.\u00a0Wiebe\u00a0(eds), Proceedings of the 2nd Workshop on Argumentation Mining, ArgMining@HLT-NAACL 2015, June 4, 2015, Denver, Colorado, USA, ACL, 2015."},{"key":"ref012","unstructured":"G.\u00a0Collell and M.F.\u00a0Moens, Submitted (2017)."},{"key":"ref013","unstructured":"G.\u00a0Collell, T.\u00a0Zhang and M.F.\u00a0Moens, Learning to predict: A fast re-constructive method to generate multimodal embeddings, in: Proceedings of the NIPS Workshop on Representation Learning in Artificial and Biological Neural Networks (MLINI 2016), 2016."},{"key":"ref014","doi-asserted-by":"crossref","unstructured":"G.\u00a0Collell, T.\u00a0Zhang and M.F.\u00a0Moens, Imagined visual representations as multimodal embeddings, in: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), AAAI, 2017.","DOI":"10.1609\/aaai.v31i1.11155"},{"key":"ref015","doi-asserted-by":"crossref","unstructured":"R.\u00a0Collobert and J.\u00a0Weston, A unified architecture for natural language processing: Deep neural networks with multitask learning, in: Proceedings of the International Conference on Machine Learning, Vol.\u00a0307, ACM, 2008, pp.\u00a0160\u2013167.","DOI":"10.1145\/1390156.1390177"},{"key":"ref016","first-page":"2493","volume":"12","author":"Collobert R.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref017","doi-asserted-by":"crossref","unstructured":"I.\u00a0Dagan, O.\u00a0Glickman and B.\u00a0Magnini, The PASCAL recognising textual entailment challenge, in: MLCW, Lecture Notes in Computer Science, Vol.\u00a03944, Springer, 2005, pp.\u00a0177\u2013190.","DOI":"10.1007\/11736790_9"},{"key":"ref018","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"ref019","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.04.001"},{"key":"ref020","doi-asserted-by":"crossref","unstructured":"K.\u00a0Deschacht and M.F.\u00a0Moens, Semi-supervised semantic role labeling using the latent words language model, in: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP), ACL, 2009, pp.\u00a021\u201329.","DOI":"10.3115\/1699510.1699514"},{"key":"ref021","unstructured":"Q.N.\u00a0Do Thi, S.\u00a0Bethard and M.F.\u00a0Moens, Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments,\n                      CoRR\n                      (2017), arXiv:1704.02709v1."},{"key":"ref022","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2449072"},{"key":"ref023","doi-asserted-by":"crossref","unstructured":"K.L.\u00a0Downing, Intelligence Emerging: Adaptivity and Search in Evolving Neural Systems, The MIT Press, 2015.","DOI":"10.7551\/mitpress\/9898.001.0001"},{"key":"ref024","doi-asserted-by":"crossref","unstructured":"D.\u00a0Elliott and F.\u00a0Keller, Image description using visual dependency representations, in: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP), ACL, 2013, pp.\u00a01292\u20131302.","DOI":"10.18653\/v1\/D13-1128"},{"key":"ref025","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2787"},{"key":"ref026","doi-asserted-by":"crossref","unstructured":"Q.\u00a0Gao, M.\u00a0Doering, S.\u00a0Yang and J.Y.\u00a0Chai, Physical causality of action verbs in grounded language understanding, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL, 2016.","DOI":"10.18653\/v1\/P16-1171"},{"key":"ref027","unstructured":"N.\u00a0Green, K.\u00a0Ashley, D.\u00a0Litman, C.\u00a0Reed and V.\u00a0Walker\u00a0(eds), Proceedings of the First Workshop on Argument Mining, Hosted by the 52nd Annual Meeting of the Association for Computational Linguistics, ArgMining@ACL 2014, June 26, 2014, Baltimore, Maryland, USA, ACL, 2014."},{"key":"ref028","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00209"},{"key":"ref029","doi-asserted-by":"crossref","unstructured":"I.\u00a0Habernal and I.\u00a0Gurevych, Argumentation mining in user-generated Web discourse,\n                      Computational Linguistics\n                      (2017) abs\/1601.02403.","DOI":"10.1162\/COLI_a_00276"},{"key":"ref030","doi-asserted-by":"crossref","unstructured":"J.\u00a0Henderson and D.N.\u00a0Popa, A vector space for distributional semantics for entailment, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL, 2016, pp.\u00a02052\u20132062.","DOI":"10.18653\/v1\/P16-1193"},{"key":"ref031","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00183"},{"key":"ref032","doi-asserted-by":"crossref","unstructured":"T.\u00a0Hofmann, Probabilistic latent semantic indexing, in: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 1999), ACM, 1999, pp.\u00a050\u201357.","DOI":"10.1145\/312624.312649"},{"key":"ref033","unstructured":"B.\u00a0Jans, S.\u00a0Bethard, I.\u00a0Vulic and M.F.\u00a0Moens, Skip n-grams and ranking functions for predicting script events, in: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2012), ACL, 2012, pp.\u00a0336\u2013344."},{"key":"ref034","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2014.06.001"},{"key":"ref035","doi-asserted-by":"crossref","unstructured":"C.A.\u00a0Kurby and J.M.\u00a0Zacks, Situation models in naturalistic comprehension, Cambridge University Press, 2015, pp.\u00a059\u201376.","DOI":"10.1017\/CBO9781107323667.004"},{"key":"ref036","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref037","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-linguist-030514-125312"},{"key":"ref038","doi-asserted-by":"crossref","unstructured":"X.\u00a0Lin and D.\u00a0Parikh, Don\u2019t just listen, use your imagination: Leveraging visual common sense for non-visual tasks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 2015, pp.\u00a02984\u20132993.","DOI":"10.1109\/CVPR.2015.7298917"},{"issue":"99","key":"ref039","first-page":"1","author":"Ludwig O.","year":"2017","journal-title":"IEEE Transactions on Computational Intelligence and AI in Games"},{"key":"ref040","doi-asserted-by":"crossref","unstructured":"M.\u00a0Malinowski, M.\u00a0Rohrbach and M.\u00a0Fritz, Ask your neurons: A neural-based approach to answering questions about images, in: Proceedings of the International Conference on Computer Vision (ICCV 2015), 2015, pp.\u00a01\u20139.","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref041","doi-asserted-by":"crossref","unstructured":"C.\u00a0Manning, Understanding human language: Can NLP and deep learning help? in: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR\u201916, ACM, New York, NY, USA, 2016, pp.\u00a01\u20131.","DOI":"10.1145\/2911451.2926732"},{"key":"ref042","unstructured":"D.\u00a0Marecek and M.\u00a0Straka, Stop-probability estimates computed on a large corpus improve unsupervised dependency parsing, in: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL, 2013, pp.\u00a0281\u2013290."},{"key":"ref043","unstructured":"T.\u00a0Mikolov, K.\u00a0Chen, G.\u00a0Corrado and J.\u00a0Dean, Efficient Estimation of Word Representations in Vector Space,\n                      CoRR\n                      (2013) abs\/1301.3781."},{"key":"ref044","unstructured":"M.\u00a0Minsky, A framework for representing knowledge, New York: McGraw-Hill, 1975, pp.\u00a0211\u2013277."},{"key":"ref045","unstructured":"J.\u00a0Mitchell and M.\u00a0Lapata, Vector-based models of semantic composition, in: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics, The Association for Computer Linguistics, 2008, pp.\u00a0236\u2013244."},{"key":"ref046","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-010-9104-x"},{"key":"ref047","doi-asserted-by":"crossref","unstructured":"A.\u00a0Modi, I.\u00a0Titov, V.\u00a0Demberg, A.\u00a0Sayeed and M.\u00a0Pinkal, Modeling semantic expectations: Using script knowledge for referent prediction,\n                      Transactions of the Association for Computational Linguistics\n                      (2016).","DOI":"10.1162\/tacl_a_00044"},{"key":"ref048","doi-asserted-by":"crossref","unstructured":"M.F.\u00a0Moens, E.\u00a0Boiy, R.\u00a0Mochales Palau and C.\u00a0Reed, Automatic detection of arguments in legal texts, in: Proceedings of the Eleventh International Conference on Artificial Intelligence and Law, ACM, 2007, pp.\u00a0225\u2013230.","DOI":"10.1145\/1276318.1276362"},{"key":"ref049","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00250"},{"key":"ref050","doi-asserted-by":"crossref","unstructured":"A.\u00a0Peldszus and M.\u00a0Stede, Joint prediction in MST-style discourse parsing for argumentation mining, in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17\u201321, 2015, 2015, pp.\u00a0938\u2013948.","DOI":"10.18653\/v1\/D15-1110"},{"key":"ref051","doi-asserted-by":"crossref","unstructured":"H.\u00a0Peng, Y.\u00a0Song and D.\u00a0Roth, Event detection and co-reference with minimal supervision, in: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP), ACL, 2016, pp.\u00a0392\u2013402.","DOI":"10.18653\/v1\/D16-1038"},{"key":"ref052","doi-asserted-by":"crossref","unstructured":"J.\u00a0Pennington, R.\u00a0Socher and C.\u00a0Manning, GloVe: Global vectors for word representation, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), ACL, 2014, pp.\u00a01532\u20131543.","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref053","doi-asserted-by":"crossref","unstructured":"K.\u00a0Pichotta and R.J.\u00a0Mooney, Learning statistical scripts with LSTM recurrent neural networks, in: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), AAAI Press, 2016, pp.\u00a02800\u20132806.","DOI":"10.1609\/aaai.v30i1.10347"},{"key":"ref054","doi-asserted-by":"crossref","unstructured":"J.\u00a0Pustejovsky, The Generative Lexicon, MIT Press, 1995.","DOI":"10.7551\/mitpress\/3225.001.0001"},{"key":"ref055","doi-asserted-by":"crossref","unstructured":"A.\u00a0Ram and K.\u00a0Moorman, Understanding Language Understanding: Computational Models of Reading, MIT Press, 1999.","DOI":"10.7551\/mitpress\/6981.001.0001"},{"key":"ref056","unstructured":"C.\u00a0Reed, K.\u00a0Ashley, C.\u00a0Cardie, N.\u00a0Green, I.\u00a0Gurevych, D.\u00a0Litman, G.\u00a0Petasis, N.\u00a0Slonim and V.\u00a0Walker\u00a0(eds), Proceedings of the Third Workshop on Argument Mining, Hosted by the 54th Annual Meeting of the Association for Computational Linguistics, ArgMining@ACL 2016, August 12, Berlin, Germany, ACL, 2016."},{"key":"ref057","unstructured":"T.\u00a0Rockt\u00e4schel, E.\u00a0Grefenstette, K.M.\u00a0Hermann, T.\u00a0Kocisky and P.\u00a0Blunsom, Reasoning about entailment with neural attention, in: Proceedings of the International Conference on Learning Representations (ICLR 2016), 2016."},{"key":"ref058","doi-asserted-by":"crossref","unstructured":"D.\u00a0Rubinstein, E.\u00a0Levi, R.\u00a0Schwartz and A.\u00a0Rappoport, How well do distributional models capture different types of semantic knowledge? in: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, ACL, 2015, pp.\u00a0726\u2013730.","DOI":"10.3115\/v1\/P15-2119"},{"key":"ref059","doi-asserted-by":"crossref","unstructured":"P.\u00a0Saint-Dizier, Challenges of argument mining: Generating an argument synthesis based on the qualia structure, in: INLG 2016 \u2013 Proceedings of the Ninth International Natural Language Generation Conference, 2016, pp.\u00a079\u201383.","DOI":"10.18653\/v1\/W16-6613"},{"key":"ref060","doi-asserted-by":"publisher","DOI":"10.1177\/1750698016645230"},{"key":"ref061","unstructured":"R.C.\u00a0Schank, Conceptual Information Processing, Amsterdam: North Holland, 1975."},{"key":"ref062","doi-asserted-by":"crossref","unstructured":"C.\u00a0Silberer and M.\u00a0Lapata, Learning grounded meaning representations with autoencoders, in: Proceedings of the 52th Annual Meeting of the Association for Computational Linguistics, ACL, 2014, pp.\u00a0721\u2013732.","DOI":"10.3115\/v1\/P14-1068"},{"key":"ref063","doi-asserted-by":"crossref","unstructured":"B.\u00a0Taskar, V.\u00a0Chatalbashev, D.\u00a0Koller and C.\u00a0Guestrin, Learning structured prediction models: A large margin approach, in: Proceedings of the 22nd International Conference on Machine Learning, ICML\u201905, ACM, New York, NY, USA, 2005, pp.\u00a0896\u2013903.","DOI":"10.1145\/1102351.1102464"},{"key":"ref064","doi-asserted-by":"crossref","unstructured":"S.\u00a0Teufel and M.\u00a0Moens, Discourse-level argumentation in scientific articles: Human and automatic annotation, in: Towards Standards and Tools for Discourse Tagging, 1999, pp.\u00a084\u201393.","DOI":"10.3115\/977035.977051"},{"key":"ref065","unstructured":"S.E.\u00a0Toulmin, The Uses of Argument, Cambridge University Press, 1958."},{"key":"ref066","first-page":"1453","volume":"6","author":"Tsochantaridis I.","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref067","unstructured":"F.H.\u00a0van Eemeren, B.\u00a0Garssen, E.C.W.\u00a0Krabbe, A.F.\u00a0Snoeck Henkemans, B.\u00a0Verheij and J.H.M.\u00a0Wagemans, Handbook of Argumentation Theory, Berlin: Springer, 1996."},{"key":"ref068","unstructured":"D.\u00a0Vernon, Artificial Cognitive Systems: A Primer, The MIT Press, 2014."},{"key":"ref069","doi-asserted-by":"crossref","unstructured":"I.\u00a0Vuli\u0107, D.\u00a0Kiela, S.\u00a0Clark and M.F.\u00a0Moens, Multi-modal representations for improved bilingual lexicon learning, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL, 2016, pp.\u00a0188\u2013194.","DOI":"10.18653\/v1\/P16-2031"},{"key":"ref070","unstructured":"J.\u00a0Weng, Natural and Artificial Intelligence, BMI Press, 2013."},{"key":"ref071","first-page":"127","volume":"28","author":"Wu J.","year":"2015","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Argument &amp; Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/AAC-170025","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/AAC-170025","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/AAC-170025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T11:53:51Z","timestamp":1777377231000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/AAC-170025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,17]]},"references-count":71,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1,31]]}},"alternative-id":["10.3233\/AAC-170025"],"URL":"https:\/\/doi.org\/10.3233\/aac-170025","relation":{},"ISSN":["1946-2166","1946-2174"],"issn-type":[{"value":"1946-2166","type":"print"},{"value":"1946-2174","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,17]]}}}