{"type":"ScholarlyArticle","title":"Learning Conceptual Space Representations of Interrelated Concepts","authors":[{"name":"Zied Bouraoui","slug":"zied-bouraoui","given":"Zied","family":"Bouraoui","affiliation":"CRIL -CNRS & Univ Artois , France"},{"name":"Steven Schockaert","slug":"steven-schockaert","given":"Steven","family":"Schockaert","affiliation":"Cardiff University , UK"}],"abstract":"Several recently proposed methods aim to learn conceptual space representations from large text collections. These learned representations associate each object from a given domain of interest with a point in a high-dimensional Euclidean space, but they do not model the concepts from this domain, and can thus not directly be used for categorization and related cognitive tasks. A natural solution is to represent concepts as Gaussians, learned from the representations of their instances, but this can only be reliably done if sufficiently many instances are given, which is often not the case. In this paper, we introduce a Bayesian model which addresses this problem by constructing informative priors from background knowledge about how the concepts of interest are interrelated with each other. We show that this leads to substantially better predictions in a knowledge base completion task.","doi":"10.24963/ijcai.2018/243","url":"https://ijcai.org/proceedings/2018/243","pdf":"https://ijcai.org/proceedings/2018/0243.pdf","markdown":"https://ijcai.org/proceedings/2018/243.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/243","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Knowledge Representation and Reasoning","track":"Main track","number":243,"pages":{"first":1760,"last":1766},"keywords":["Humans and AI: Cognitive Modeling","Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning","Natural Language Processing: Embeddings","Knowledge Representation and Reasoning: Common-Sense Reasoning"],"videos":[],"references":[{"position":1,"raw":"[Alfarone and Davis, 2015] Daniele Alfarone and Jesse Davis. Unsupervised learning of an IS-A taxonomy from a limited domain-specific corpus. In Proc. IJCAI, pages 1434-1441, 2015.","title":"Unsupervised learning of an IS-A taxonomy from a limited domain-specific corpus","authors":"Daniele Alfarone, Jesse Davis","year":"2015","venue":"Proc. IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/206"},{"position":2,"raw":"[Baader et al., 2003] Franz Baader, Diego Calvanese, Deb- orah L. McGuinness, Daniele Nardi, and Peter F. Patel- Schneider, editors. The Description Logic Handbook: Theory, Implementation, and Applications. Cambridge University Press, New York, NY, USA, 2003.","title":"The Description Logic Handbook: Theory, Implementation, and Applications","authors":"Franz Baader, Diego Calvanese, L Deborah","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bordes et al., 2013] A. Bordes, N. Usunier, A. Garcia- Duran, J. Weston, and O. Yakhnenko. Translating embed- dings for modeling multi-relational data. In Proc. NIPS, pages 2787-2795. 2013.","title":"Translating embeddings for modeling multi-relational data","authors":"A Bordes, N Usunier, A Garcia-Duran, J Weston, O Yakhnenko","year":"2013","venue":"Proc. NIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bouraoui and Schockaert, 2018] Zied Bouraoui and Steven Schockaert. Learning conceptual space representations of interrelated concepts. CoRR, abs/1805.01276, 2018.","title":"Learning conceptual space representations of interrelated concepts","authors":"Schockaert Bouraoui, Zied Bouraoui, Steven Schockaert","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bouraoui et al., 2017] Zied Bouraoui, Shoaib Jameel, and Steven Schockaert. Inductive reasoning about ontologies using conceptual spaces. In Proc. AAAI, pages 4364-4370, 2017.","title":"Inductive reasoning about ontologies using conceptual spaces","authors":"Zied Bouraoui, Shoaib Jameel, Steven Schockaert","year":"2017","venue":"Proc. AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chella et al., 1997] Antonio Chella, Marcello Frixione, and Salvatore Gaglio. A cognitive architecture for artificial vi- sion. Artif. Intell., 89(1-2):73-111, 1997.","title":"A cognitive architecture for artificial vision","authors":"Chella","year":"1997","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chella et al., 2003] Antonio Chella, Marcello Frixione, and Salvatore Gaglio. Conceptual spaces for anchoring. Robotics and Autonomous Systems, 43(2-3):193-195, 2003.","title":"Conceptual spaces for anchoring","authors":"Chella","year":"2003","venue":"Robotics and Autonomous Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Douven et al., 2013] I. Douven, L. Decock, R. Dietz, and P. Égré. Vagueness: A conceptual spaces approach. Jour- nal of Philosophical Logic, 42:137-160, 2013.","title":"Vagueness: A conceptual spaces approach","authors":"Douven","year":"2013","venue":"Journal of Philosophical Logic","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Forth et al., 2010] J. Forth, G. A Wiggins, and A. McLean. Unifying conceptual spaces: Concept formation in musi- cal creative systems. Minds and Machines, 20:503-532, 2010.","title":"Unifying conceptual spaces: Concept formation in musical creative systems","authors":"J Forth, G A Wiggins, A Mclean","year":"2010","venue":"Minds and Machines","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gärdenfors, 2000] P. Gärdenfors. Conceptual Spaces: The Geometry of Thought. MIT Press, 2000.","title":"Conceptual Spaces: The Geometry of Thought","authors":"P Gärdenfors","year":"2000","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"Marti A Hearst. Automatic acquisition of hy- ponyms from large text corpora. In Proc. COLING, pages 539-545, 1992.","title":"Automatic acquisition of hyponyms from large text corpora","authors":"A Marti, Hearst","year":"1992","venue":"Proc. COLING","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jäger, 2009] Gerhard Jäger. Natural color categories are convex sets. In 17th Amsterdam Colloquium on Logic, Language and Meaning, pages 11-20, 2009.","title":"Natural color categories are convex sets","authors":"Gerhard Jäger","year":"2009","venue":"17th Amsterdam Colloquium on Logic, Language and Meaning","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jameel et al., 2017] Shoaib Jameel, Zied Bouraoui, and Steven Schockaert. MEmbER: Max-margin based embed- dings for entity retrieval. In Proc. SIGIR, pages 783-792, 2017.","title":"MEmbER: Max-margin based embeddings for entity retrieval","authors":"Shoaib Jameel, Zied Bouraoui, Steven Schockaert","year":"2017","venue":"Proc. SIGIR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kok and Domingos, 2007] Stanley Kok and Pedro Domin- gos. Statistical predicate invention. In Proc. ICML, pages 433-440, 2007.","title":"Statistical predicate invention","authors":"Domingos ; Kok, Pedro Kok, Domingos","year":"2007","venue":"Proc. ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kozareva and Hovy, 2010] Zornitsa Kozareva and Eduard Hovy. A semi-supervised method to learn and construct taxonomies using the web. In Proc. EMNLP, pages 1110- 1118, 2010.","title":"Zornitsa Kozareva and Eduard Hovy. A semi-supervised method to learn and construct taxonomies using the web","authors":"Hovy Kozareva","year":"2010","venue":"Proc. EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mikolov et al., 2013] Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. Linguistic regularities in continuous space word representations. In Proc. NAACL-HLT, pages 746-751, 2013.","title":"Linguistic regularities in continuous space word representations","authors":"Mikolov","year":"2013","venue":"Proc. NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mintz et al., 2009] Mike Mintz, Steven Bills, Rion Snow, and Dan Jurafsky. Distant supervision for relation extrac- tion without labeled data. In Proc. ACL, pages 1003-1011, 2009.","title":"Distant supervision for relation extraction without labeled data","authors":"Mike Mintz, Steven Bills, Rion Snow, Dan Jurafsky","year":"2009","venue":"Proc. ACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Murphy, 2007] Kevin Murphy. Conjugate Bayesian analy- sis of the Gaussian distribution. Technical report, Univer- sity of British Columbia, 2007.","title":"Conjugate Bayesian analysis of the Gaussian distribution","authors":"Kevin Murphy","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Neelakantan and Chang, 2015] Arvind Neelakantan and Ming-Wei Chang. Inferring missing entity type in- stances for knowledge base completion: New dataset and methods. In Proc. NAACL, pages 515-525, 2015.","title":"Inferring missing entity type instances for knowledge base completion: New dataset and methods","authors":"Chang ; Neelakantan, Arvind Neelakantan, Ming-Wei Chang","year":"2015","venue":"Proc. NAACL","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Palatucci et al., 2009] Mark Palatucci, Dean Pomerleau, Geoffrey E Hinton, and Tom M Mitchell. Zero-shot learn- ing with semantic output codes. In Proc. NIPS, pages 1410-1418, 2009.","title":"Zero-shot learning with semantic output codes","authors":"Mark Palatucci, Dean Pomerleau, Geoffrey E Hinton, Tom M Mitchell","year":"2009","venue":"Proc. NIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Riedel et al., 2010] Sebastian Riedel, Limin Yao, and An- drew McCallum. Modeling relations and their mentions without labeled text. In Proc. ECML/PKDD, pages 148- 163, 2010.","title":"Modeling relations and their mentions without labeled text","authors":"Sebastian Riedel, Limin Yao, Andrew Mccallum","year":"2010","venue":"Proc. ECML/PKDD","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rocktäschel and Riedel, 2016] Tim Rocktäschel and Sebas- tian Riedel. Learning knowledge base inference with neu- ral theorem provers. In Proceedings of the 5th Workshop on Automated Knowledge Base Construction, pages 45- 50, 2016.","title":"Tim Rocktäschel and Sebastian Riedel. Learning knowledge base inference with neural theorem provers","authors":"Riedel Rocktäschel","year":"2016","venue":"Proceedings of the 5th Workshop on Automated Knowledge Base Construction","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Romera-Paredes and Torr, 2015] Bernardino Romera- Paredes and Philip Torr. An embarrassingly simple approach to zero-shot learning. In Proc. ICML, pages 2152-2161, 2015.","title":"An embarrassingly simple approach to zero-shot learning","authors":"Bernardino Romera, - Paredes, Philip Torr","year":"2015","venue":"Proc. ICML","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Rosch, 1973] Eleanor H Rosch. Natural categories. Cogni- tive Psychology, 4(3):328-350, 1973.","title":"Natural categories","authors":"Eleanor H Rosch","year":"1973","venue":"Cognitive Psychology","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Rosseel, 2002] Yves Rosseel. Mixture models of catego- rization. Journal of Mathematical Psychology, 46:178- 210, 2002.","title":"Mixture models of categorization","authors":"Yves Rosseel, Rosseel","year":"2002","venue":"Journal of Mathematical Psychology","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Socher et al., 2013] Richard Socher, Milind Ganjoo, Christopher D Manning, and Andrew Ng. Zero-shot learning through cross-modal transfer. In Proc. NIPS, pages 935-943, 2013.","title":"Zero-shot learning through cross-modal transfer","authors":"Richard Socher, Milind Ganjoo, Christopher D Manning, Andrew Ng","year":"2013","venue":"Proc. NIPS","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sourek et al., 2016] Gustav Sourek, Suresh Manandhar, Filip Zelezný, Steven Schockaert, and Ondrej Kuzelka. Learning predictive categories using lifted relational neu- ral networks. In Proc. ILP, pages 108-119, 2016.","title":"Learning predictive categories using lifted relational neural networks","authors":"Sourek","year":"2016","venue":"Proc. ILP","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Vylomova et al., 2016] Ekaterina Vylomova, Laura Rimell, Trevor Cohn, and Timothy Baldwin. Take and took, gag- gle and goose, book and read: Evaluating the utility of vector differences for lexical relation learning. In Proc. ACL, 2016.","title":"Take and took, gaggle and goose, book and read: Evaluating the utility of vector differences for lexical relation learning","authors":"Ekaterina Vylomova, Laura Rimell, Trevor Cohn, Timothy Baldwin","year":"2016","venue":"Proc. ACL","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}