Abstract
Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases. We present a method for performing deductive reasoning directly in such a vector space, combining analogy, association, and deduction in a straightforward way at each step in a chain of reasoning, drawing on knowledge from diverse sources and ontologies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In some special cases, the error in one gap of the chain will largely cancel out with the error at another gap. When this happens, the system has found an analogous relation. This is discussed in the section Analogical Properties of Semantic Spaces below.
- 2.
Boole and DeMorgan originally formulated propositional logic as a special case of the logic of subsets [5].
- 3.
If \(\varvec{a}\) and \(\varvec{b}\) are approximately orthogonal unit vectors, then the similarity between the two will be \(\frac{\sqrt{2}}{2}\). This is much higher than the expected similarity between any two terms selected from the space. See [20] for details.
- 4.
Notice that addition is used as AND rather than OR when combining B with A and \(A\Rightarrow B\) (see the caption of Table 1 for why this is acceptable). At any rate, the notion of cancelling out with modus ponens still holds.
- 5.
When a direct chain of reasoning is possible, such links won’t happen– the analogy, being inexact, has a higher cost than the direct link.
- 6.
Along the same lines, [22] describes a more intricate method of locating particular word senses in the vector space.
- 7.
Deductive reasoning systems typically use either forwards or backwards inference. This system uses “middle out” inference, that doesn’t begin at either end but is a holistic procedure happening all along the chain at once.
- 8.
Notice that the fourth, less relevant, fact is also relating a food to a color.
- 9.
In fact, they may form a multistranded rope rather than a chain– the “elastic-net” [23] parameter in LASSO can be used to encourage or discourage finding alternative equally good paths for part or all of the chain.
- 10.
A slightly more complicated cost function can be used to encourage the lowest cost path to follow analogical connections as well.
References
Baroni, M., Zamparelli, R.: Nouns are vectors, adjectives are matrices: representing adjective-noun constructions in semantic space. In: 2010 Conference on Empirical Methods in Natural Language Processing, pp. 1183–1193. ACL, October 2010
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, pp. 2787–2795 (2013)
Buchanan, B.G., Shortliffe, E.H.: Rule-Based Expert Systems: The MYCIN Experiments. Addison-Wesley, Reading (1984)
Dumais, S.T., Furnas, G.W., Landauer, T.K., Deerwester, S., Harshman, R.: Using latent semantic analysis to improve access to textual information. In: SIGCHI Conference, pp. 281–285. ACM, May 1988
Ellerman, D.: The logic of partitions: introduction to the dual of the logic of subsets. Rev. Symbolic Logic 3(2), 287–350 (2010)
Freitas, A., Curry, E.: Natural language queries over heterogeneous linked data graphs: a distributional-compositional semantics approach. In: 19th International Conference on Intelligent User Interfaces. ACM (2014)
Gayler, R.: Vector symbolic architectures answer Jackendoff’s challenges for cognitive neuroscience. In: Slezak, P. (ed.) ICCS/ASCS International Conference on Cognitive Science, pp. 133–138. University of New South Wales, CogPrints, Sydney (2003)
Grefenstette, E., Sadrzadeh, M.: Experimental support for a categorical compositional distributional model of meaning. In: Conference on Empirical Methods in Natural Language Processing, pp. 1394–1404. ACL, July 2011
Kanerva, P.: Sparse Distributed Memory. MIT press, Cambridge (1988)
Kiros, R., Zhu, Y., Salakhutdinov, R.R., Zemel, R., Urtasun, R., Torralba, A., Fidler, S.: Skip-thought vectors. In: NIPS, pp. 3294–3302 (2015)
Knowlton, B., Morrison, R., Hummel, J., Holyoak, K.: A neurocomputational system for relational reasoning. Trends Cogn. Sci. 16(7), 373–381 (2012)
Lee, M., He, X., Yih, W.T., Gao, J., Deng, L., Smolensky, P.: Reasoning in vector space: an exploratory study of question answering. arXiv:1511.06426 (2015)
Levy, S.D.: Distributed representation of compositional structure. In: Rabual, J.R., Dorado, J., Pazos, A. (eds.) Encyclopedia of Artificial Intelligence. IGI Publishing, Hershey (2008)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Rocktäschel, T., Riedel, S.: Learning knowledge base inference with neural theorem provers. In: AKBC, pp. 45–50 (2016)
Summers-Stay, D., Voss, C., Cassidy, T.: Using a distributional semantic vector space with a knowledge base for reasoning in uncertain conditions. Biologically Inspired Cogn. Architectures 16, 34–44 (2016)
Turney, P.D.: Measuring semantic similarity by latent relational analysis. arXiv preprint cs/0508053 (2005)
Wang, H., Onishi, T., Gimpel, K., McAllester, D.: Emergent logical structure in vector representations of neural readers. arXiv preprint arXiv:1611.07954 (2016)
West, R., Gabrilovich, E., Murphy, K., Sun, S., Gupta, R., Lin, D.: Knowledge base completion via search-based question answering. In: 23rd International Conference on World Wide Web, pp. 515–526. ACM, April 2014
Widdows, D., Peters, S.: Word vectors and quantum logic: experiments with negation and disjunction. Math. Lang. 8, 141–154 (2003)
Widdows, D., Cohen, T.: Reasoning with vectors: a continuous model for fast robust inference. Logic J. IGPL 23(2), 141–173 (2014). jzu028
Yu, M., Dredze, M.: Improving lexical embeddings with semantic knowledge. In: ACL, no. 2, pp. 545–550, June 2014
Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Royal Stat. Soc. Stat. Methodol. 67(2), 301–320 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Summers-Stay, D. (2017). Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph. In: Everitt, T., Goertzel, B., Potapov, A. (eds) Artificial General Intelligence. AGI 2017. Lecture Notes in Computer Science(), vol 10414. Springer, Cham. https://doi.org/10.1007/978-3-319-63703-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-63703-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-63702-0
Online ISBN: 978-3-319-63703-7
eBook Packages: Computer ScienceComputer Science (R0)