Graded hyponymy for compositional distributional semantics

• Autorzy: Bankova D. , Coecke B. , Lewis M. , Marsden D.

Identyfikatory

DOI

10.15398/jlm.v6i2.230

• Języki publikacji: EN

Abstrakty

EN

The categorical compositional distributional model of natural language provides a conceptually motivated procedure to compute the meaning of a sentence, given its grammatical structure and the meanings of its words. This approach has outperformed other models in mainstream empirical language processing tasks, but lacks an effective model of lexical entailment. We address this shortcoming by exploiting the freedom in our abstract categorical framework to change our choice of semantic model. This allows us to describe hyponymy as a graded order on meanings, using models of partial information used in quantum computation. Quantum logic embeds in this graded order.

Słowa kluczowe

EN

categorical semantics; compositional semantics; distributional semantics; computational linguistics; entailment; density operator

• Wydawca: Instytut Podstaw Informatyki PAN
• Czasopismo: Journal of Language Modelling
• Rocznik: 2018
• Tom: Vol. 6, No. 2
• Strony: 225--260
• Opis fizyczny: Bibliogr. 46 poz., rys., tab.

Twórcy

autor

Bankova D.

• Quantum Group, University of Oxford

autor

Coecke B.

• Quantum Group, University of Oxford

autor

Lewis M.

• ILLC, University of Amsterdam

autor

Marsden D.

• Quantum Group, University of Oxford

Bibliografia

• [1] Esma Balkır (2014), Using Density Matrices in a Compositional Distributional odel of Meaning, Master’s thesis, University of Oxford, http://www.cs.ox.ac.uk/people/bob.coecke/Esma.pdf.
• [2] Esma Balkır, Mehrnoosh Sadrzadeh, and Bob Coecke (2016), Distributional Sentence Entailment Using Density Matrices, in Mohammad T. Hajiaghayi and Mohammad R. Mousavi, editors, Topics in Theoretical Computer Science, volume 9541 of Lecture Notes in Computer Science, pp. 1-22, Springer, Cham, https://doi.org/10.1007/978-3-319-28678-5_1.
• [3] Dea Bankova (2015), Comparing Meaning in Language and Cognition: P-Hyponymy, Concept Combination, Asymmetric Similarity, Master’s thesis, University of Oxford, http://www.cs.ox.ac.uk/people/bob.coecke/Dea.pdf.
• [4] Marco Baroni, Raffaella Bernardi, Ngoc-Quynh Do, and Chung-chieh Shan (2012), Entailment above the word level in distributional semantics, in Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 23-32, Association for Computational Linguistics, http://aclweb.org/anthology/E12-1004.
• [5] Marco Baroni and Roberto Zamparelli (2010), Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space, in Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 1183-1193, Association for Computational Linguistics, http://aclweb.org/anthology/D10-1115.
• [6] Jon Barwise and Robin Cooper (1981), Generalized Quantifiers and Natural Language, Linguistics and Philosophy, 4:159-219.
• [7] Steven Bird, Ewan Klein, and Edward Loper (2009), Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit, O’Reilly Media, Inc.
• [8] Garrett Birkhoff and John von Neumann (1936), The Logic of Quantum Mechanics, Annals of Mathematics, 37 (4):823-843, ISSN 0003486X, http://www.jstor.org/stable/1968621.
• [9] William Blacoe, Elham Kashefi, and Mirella Lapata (2013), A Quantum-Theoretic Approach to Distributional Semantics, in Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 847-857, Association for Computational Linguistics, http://aclweb.org/anthology/N13-1105.
• [10] Felix Bloch (1946), Nuclear Induction, Phys. Rev., 70:460-474, doi: 10.1103/PhysRev.70.460, https://link.aps.org/doi/10.1103/PhysRev.70.460.
• [11] Samuel R. Bowman, Christopher Potts, and Christopher D. Manning (2015), Recursive Neural Networks Can Learn Logical Semantics, in Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, pp. 12-21, Association for Computational Linguistics, doi: 10.18653/v1/W15-4002, http://aclweb.org/anthology/W15-4002.
• [12] Daoud Clarke (2009), Context-theoretic Semantics for Natural Language: An Overview, in Proceedings of the Workshop on Geometrical Models of Natural Language Semantics, GEMS ’09, pp. 112-119, Association for Computational Linguistics, Stroudsburg, PA, USA, http://dl.acm.org/citation.cfm?id=1705415.1705430.
• [13] Bob Coecke, Edward Grefenstette, and Mehrnoosh Sadrzadeh (2013), Lambek vs. Lambek: Functorial vector space semantics and string diagrams for Lambek calculus, Annals of Pure and Applied Logic, 164 (11):1079-1100, ISSN 0168-0072, https://doi.org/10.1016/j.apal.2013.05.009, special issue on Seventh Workshop on Games for Logic and Programming Languages (GaLoP VII).
• [14] Bob Coecke and Keye Martin (2011), A partial order on classical and quantum states, in New Structures for Physics, pp. 593-683, Springer.
• [15] Bob Coecke and Éric Oliver Paquette (2011), Categories for the practising physicist, in New Structures for Physics, pp. 173-286, Springer, https://doi.org/10.1007/978-3-642-12821-9_3.
• [16] Bob Coecke, Mehrnoosh Sadrzadeh, and Stephen J Clark (2010), Mathematical Foundations for a Compositional Distributional Model of Meaning, Linguistic Analysis, 36 (1):345-384.
• [17] Ido Dagan, Oren Glickman, and Bernardo Magnini (2006), The PASCAL Recognising Textual Entailment Challenge, in Joaquin Quiñonero-Candela, Ido Dagan, Bernardo Magnini, and Florence d’Alché Buc, editors, Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Textual Entailment, volume 3944 of Lecture Notes in Computer Science, pp. 177-190, Springer, Berlin, Heidelberg, https://doi.org/10.1007/11736790_9.
• [18] Ellie D’Hondt and Prakash Panangaden (2006), Quantum Weakest Preconditions, Mathematical Structures in Computer Science, 16 (3):429-451, https://doi.org/10.1017/S0960129506005251.
• [19] Maayan Geffet and Ido Dagan (2005), The Distributional Inclusion Hypotheses and Lexical Entailment, in Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pp. 107-114, Association for Computational Linguistics, http://aclweb.org/anthology/P05-1014.
• [20] Edward Grefenstette, Georgiana Dinu, Yi Zhang, Mehrnoosh Sadrzadeh, and Marco Baroni (2013), Multi-Step Regression Learning for Compositional Distributional Semantics, in Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013) – Long Papers, pp. 131-142, Association for Computational Linguistics, http://aclweb.org/anthology/W13-0112.
• [21] Edward Grefenstette and Mehrnoosh Sadrzadeh (2011), Experimental Support for a Categorical Compositional Distributional Model of Meaning, in Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp. 1394-1404, Association for Computational Linguistics, http://aclweb.org/anthology/D11-1129.
• [22] Jules Hedges and Mehrnoosh Sadrzadeh (2016), A Generalised Quantifier Theory of Natural Language in Categorical Compositional Distributional Semantics with Bialgebras, CoRR, abs/1602.01635, http://arxiv.org/abs/1602.01635.
• [23] Dimitri Kartsaklis (2015), Compositional Distributional Semantics with Compact Closed Categories and Frobenius Algebras, Ph.D. thesis, University of Oxford, https://arxiv.org/abs/1505.00138.
• [24] Dimitri Kartsaklis, Matthew Purver, and Mehrnoosh Sadrzadeh (2016), Verb Phrase Ellipsis using Frobenius Algebras in Categorical Compositional Distributional Semantics, in DSALT Workshop, European Summer School on Logic, Language and Information, https://www.eecs.qmul.ac.uk/~mpurver/papers/kartsaklis-et-al16dsalt.pdf.
• [25] Dimitri Kartsaklis, Mehrnoosh Sadrzadeh, and Stephen Pulman (2012), A Unified Sentence Space for Categorical Distributional-Compositional Semantics: Theory and Experiments, in Proceedings of COLING 2012: Posters, pp. 549-558, The COLING 2012 Organizing Committee, http://aclweb.org/anthology/C12-2054.
• [26] Graham M. Kelly and Miguel L. Laplaza (1980), Coherence for compact closed categories, Journal of Pure and Applied Algebra, 19:193-213, ISSN 0022-4049, https://doi.org/10.1016/0022-4049(80)90101-2.
• [27] Douwe Kiela, Laura Rimell, Ivan Vulić, and Stephen Clark (2015), Exploiting Image Generality for Lexical Entailment Detection, in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 119-124, Association for Computational Linguistics, doi: 10.3115/v1/P15-2020, http://aclweb.org/anthology/P15-2020.
• [28] Lili Kotlerman, Ido Dagan, Idan Szpektor, and Maayan Zhitomirsky-Geffet (2010), Directional distributional similarity for lexical inference, Natural Language Engineering, 16 (4):359-389, https://doi.org/10.1017/S1351324910000124.
• [29] Dexter Kozen (1983), A Probabilistic PDL, in David S. Johnson, Ronald Fagin, Michael L. Fredman, David Harel, Richard M. Karp, Nancy A. Lynch, Christos H. Papadimitriou, Ronald L. Rivest, Walter L. Ruzzo, and Joel I. Seiferas, editors, Proceedings of the 15th Annual ACM Symposium on Theory of Computing, 25-27 April, 1983, Boston, Massachusetts, USA, pp. 291-297, ACM, https://doi.org/10.1145/800061.808758.
• [30] Joachim Lambek (1997), Type Grammar Revisited, in Alain Lecomte, François Lamarche, and Guy Perrier, editors, Logical Aspects of Computational Linguistics, Second International Conference, LACL ’97, Nancy, France, September 22-24, 1997, Selected Papers, volume 1582 of Lecture Notes in Computer Science, pp. 1-27, Springer, ISBN 3-540-65751-7, https://doi.org/10.1007/3-540-48975-4_1.
• [31] Alessandro Lenci and Giulia Benotto (2012), Identifying hypernyms in distributional semantic spaces, in *SEM 2012: The First Joint Conference on Lexical and Computational Semantics – Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012), pp. 75-79, Association for Computational Linguistics, http://aclweb.org/anthology/S12-1012.
• [32] Karl Löwner (1934), Über monotone Matrixfunktionen, Mathematische Zeitschrift, 38 (1):177-216.
• [33] Bill MacCartney and Christopher D. Manning (2007), Natural Logic for Textual Inference, in Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, RTE ’07, pp. 193-200, Association for Computational Linguistics, Stroudsburg, PA, USA, http://dl.acm.org/citation.cfm?id=1654536.1654575.
• [34] George A. Miller (1995), WordNet: A Lexical Database for English, Communinications of the ACM, 38 (11):39-41, ISSN 0001-0782, doi: 10.1145/219717.219748, http://doi.acm.org/10.1145/219717.219748.
• [35] Michael A. Nielsen and Isaac L. Chuang (2011), Quantum Computation and Quantum Information: 10th Anniversary Edition, Cambridge University Press, New York, NY, USA, 10th edition, ISBN 1107002176, 9781107002173.
• [36] Jeffrey Pennington, Richard Socher, and Christopher Manning (2014), Glove: Global Vectors for Word Representation, in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532-1543, Association for Computational Linguistics, doi: 10.3115/v1/D14-1162, http://aclweb.org/anthology/D14-1162.
• [37] Robin Piedeleu (2014), Ambiguity in Categorical Models of Meaning, Master’s thesis, University of Oxford, http://www.cs.ox.ac.uk/people/bob.coecke/Robin.pdf.
• [38] Robin Piedeleu, Dimitri Kartsaklis, Bob Coecke, and Mehrnoosh Sadrzadeh (2015), Open System Categorical Quantum Semantics in Natural Language Processing, in Lawrence S. Moss and Pawel Soboci’nski, editors, 6th Conference on Algebra and Coalgebra in Computer Science, CALCO 2015, June 24-26, 2015, Nijmegen, The Netherlands, volume 35 of LIPIcs, pp. 270-289, Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, ISBN 978-3-939897-84-2, https://doi.org/10.4230/LIPIcs.CALCO.2015.270.
• [39] Anne Preller and Mehrnoosh Sadrzadeh (2011), Bell States and Negative Sentences in the Distributed Model of Meaning, Electronic Notes in Theoretical Computer Science, 270 (2):141-153, ISSN 1571-0661, https://doi.org/10.1016/j.entcs.2011.01.028, proceedings of the 6th International Workshop on Quantum Physics and Logic (QPL 2009).
• [40] C. J. van Rijsbergen (2004), The Geometry of Information Retrieval, Cambridge University Press, New York, NY, USA, ISBN 0521838053.
• [41] Laura Rimell (2014), Distributional Lexical Entailment by Topic Coherence, in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, pp. 511-519, Association for Computational Linguistics, doi:10.3115/v1/E14-1054, http://aclweb.org/anthology/E14-1054.
• [42] Mehrnoosh Sadrzadeh, Dimitri Kartsaklis, and Esma Balkir (2018), Sentence entailment in compositional distributional semantics, Annals of Mathematics and Artificial Intelligence, 82 (4):189-218, https://doi.org/10.1007/s10472-017-9570-x.
• [43] Peter Selinger (2007), Dagger Compact Closed Categories and Completely Positive Maps: (Extended Abstract), Electronic Notes in Theoretical Computer Science, 170:139-163, ISSN 1571-0661, https://doi.org/10.1016/j.entcs.2006.12.018, proceedings of the 3rd International Workshop on Quantum Programming Languages (QPL 2005).
• [44] Julie Weeds, David Weir, and Diana McCarthy (2004), Characterising Measures of Lexical Distributional Similarity, in COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics, http://aclweb.org/anthology/C04-1146.
• [45] Hermann Weyl (1912), Das asymptotische Verteilungsgesetz der Eigenwerte linearer partieller Differentialgleichungen (mit einer Anwendung auf die Theorie der Hohlraumstrahlung), Mathematische Annalen, 71 (4):441-479.
• [46] Dominic Widdows and Stanley Peters (2003), Word vectors and quantum logic: Experiments with negation and disjunction, in Proceedings of Mathematics of Language 8, pp. 141-154.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).