Advertisement

Syntax-Semantic Mapping for General Intelligence: Language Comprehension as Hypergraph Homomorphism, Language Generation as Constraint Satisfaction

  • Ruiting Lian
  • Ben Goertzel
  • Shujing Ke
  • Jade O’Neill
  • Keyvan Sadeghi
  • Simon Shiu
  • Dingjie Wang
  • Oliver Watkins
  • Gino Yu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7716)

Abstract

A new approach to translating between natural language expressions and hypergraph-based semantic knowledge representations is proposed. Language comprehension is formulated in terms of homomorphisms mapping syntactic parse trees into semantic hypergraphs, and language generation as constraint satisfaction based on constraints derived via applying the inverse relations of these homomorphisms. This provides an elegant approach to implementing semantically savvy NLP systems, and also to thinking about the feedbacks between syntactic and semantic processing that are the crux of generally intelligent NLP. A prototype of the approach created using the link parser and the OpenCog Atom semantic representation is described, and initial results presented. Routes to extending this prototype into something useful for aiding generally intelligent dialogue systems are discussed.

Keywords

Constraint Satisfaction Constraint Satisfaction Problem Language Comprehension General Intelligence Language Generation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Adams, S., Goertzel, B., et al.: Toward a roadmap toward human-level artificial general intelligence (2010) (subm. for publication)Google Scholar
  2. 2.
    Goertzel, B.: A pragmatic path toward endowing virtually-embodied ais with human-level linguistic capability. In: IEEE World Congress on Computational Intelligence, WCCI (2008)Google Scholar
  3. 3.
    Goertzel, B., et al.: Opencogbot: An integrative architecture for embodied agi. In: Proc. of ICAI 2010, Beijing (2010)Google Scholar
  4. 4.
    Goertzel, B., Pinto, H., Pennachin, C., Goertzel, I.F.: Using dependency parsing and probabilistic inference to extract relationships between genes, proteins and malignancies implicit among multiple biomedical research abstracts. In: Proc. of Bio-NLP 2006 (2006)Google Scholar
  5. 5.
    Goertzel, B., et al.: A general intelligence oriented architecture for embodied natural language processing. In: Proc. of the Third Conf. on Artificial General Intelligence, AGI 2010. Atlantis Press (2010)Google Scholar
  6. 6.
    Lian, R., Goertzel, B., et al.: Language generation via glocal similarity matching. Neurocomputing (2010)Google Scholar
  7. 7.
    Goertzel, B., Pennachin, C., et al.: An integrative methodology for teaching embodied non-linguistic agents, applied to virtual animals in second life. In: Proc. of the First Conf. on AGI. IOS Press (2008)Google Scholar
  8. 8.
    Goertzel, B., Pitt, J., Cai, Z., Wigmore, J., Huang, D., Geisweiller, N., Lian, R., Yu, G.: Integrative general intelligence for controlling game ai in a minecraft-like environment. In: Proc. of BICA 2011 (2011)Google Scholar
  9. 9.
    Goertzel, B.: The Hidden Pattern. Brown Walker (2006)Google Scholar
  10. 10.
    Sleator, D., Temperley, D.: Parsing english with a link grammar. In: Third International Workshop on Parsing Technologies (1993)Google Scholar
  11. 11.
    Voloshin, V.: Introduction to Graph and Hypergraph Theory. Nova Science (2009)Google Scholar
  12. 12.
    Cai, Z., Goertzel, B., Zhou, C., Zhang, Y., Jiang, M., Yu, G.: Dynamics of a computational affective model inspired by dörner’s psi theory. Cognitive Systems Research (2011)Google Scholar
  13. 13.
    Goertzel, B.: Cognitive synergy: A universal principle of feasible general intelligence? In: ICCI 2009, Hong Kong (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Ruiting Lian
    • 2
    • 4
  • Ben Goertzel
    • 2
    • 3
    • 4
  • Shujing Ke
    • 1
    • 2
    • 4
  • Jade O’Neill
    • 1
  • Keyvan Sadeghi
    • 2
  • Simon Shiu
    • 1
  • Dingjie Wang
    • 2
    • 4
  • Oliver Watkins
    • 2
  • Gino Yu
    • 2
  1. 1.Dept. of Computer ScienceHong Kong Poly UHong Kong
  2. 2.School of DesignHong Kong Poly UHong Kong
  3. 3.Novamente LLCUSA
  4. 4.Dept. of Cognitive ScienceXiamen UniversityChina

Personalised recommendations