Semantic decomposition (natural language processing)

From HandWiki

A semantic decomposition is an algorithm that breaks down the meanings of phrases or concepts into less complex concepts.[1] The result of a semantic decomposition is a representation of meaning. This representation can be used for tasks, such as those related to artificial intelligence or machine learning. Semantic decomposition is common in natural language processing applications.

The basic idea of a semantic decomposition is taken from the learning skills of adult humans, where words are explained using other words. It is based on Meaning-text theory. Meaning-text theory is used as a theoretical linguistic framework to describe the meaning of concepts with other concepts.

Background

Given that an AI does not inherently have language, it is unable to think about the meanings behind the words of a language. An artificial notion of meaning needs to be created for a strong AI to emerge.[2]

Creating an artificial representation of meaning requires the analysis of what meaning is. Many terms are associated with meaning, including semantics, pragmatics, knowledge and understanding or word sense.[3] Each term describes a particular aspect of meaning, and contributes to a multitude of theories explaining what meaning is. These theories need to be analyzed further to develop an artificial notion of meaning best fit for our current state of knowledge.

Graph representations

Abstract approach on how knowledge representation and reasoning allow a problem specific solution (answer) to a given problem (questions)

Representing meaning as a graph is one of the two ways that both an AI cognition and a linguistic researcher think about meaning (connectionist view). Logicians utilize a formal representation of meaning to build upon the idea of symbolic representation, whereas description logics describe languages and the meaning of symbols. This contention between 'neat' and 'scruffy' techniques has been discussed since the 1970s.[4]

Research has so far identified semantic measures and with that word-sense disambiguation (WSD) - the differentiation of meaning of words - as the main problem of language understanding.[5] As an AI-complete environment, WSD is a core problem of natural language understanding.[6][7] AI approaches that use knowledge-given reasoning creates a notion of meaning combining the state of the art knowledge of natural meaning with the symbolic and connectionist formalization of meaning for AI. The abstract approach is shown in Figure. First, a connectionist knowledge representation is created as a semantic network consisting of concepts and their relations to serve as the basis for the representation of meaning.[8][9][10][11]

This graph is built out of different knowledge sources like WordNet, Wiktionary, and BabelNET. The graph is created by lexical decomposition that recursively breaks each concept semantically down into a set of semantic primes.[1] The primes are taken from the theory of Natural Semantic Metalanguage,[12] which has been analyzed for usefulness in formal languages.[13] Upon this graph marker passing[14][15][16] is used to create the dynamic part of meaning representing thoughts.[17] The marker passing algorithm, where symbolic information is passed along relations form one concept to another, uses node and edge interpretation to guide its markers. The node and edge interpretation model is the symbolic influence of certain concepts.

Future work uses the created representation of meaning to build heuristics and evaluate them through capability matching and agent planning, chatbots or other applications of natural language understanding.

See also

References

  1. 1.0 1.1 Riemer, Nick (2015-07-30) (in en). The Routledge Handbook of Semantics. Routledge. ISBN 9781317412441. https://books.google.com/books?id=05lGCgAAQBAJ. 
  2. Michael, Loizos (2015-07-27). Jumping to conclusions. CEUR-WS.org. pp. 43–49. http://dl.acm.org/citation.cfm?id=2907094.2907102. 
  3. Löbner, Sebastian (2015-05-19) (in de). Semantik: Eine Einführung. Walter de Gruyter GmbH & Co KG. ISBN 9783110350906. https://books.google.com/books?id=UZ2lCQAAQBAJ. 
  4. Minsky, Marvin L. (1991-06-15). "Logical Versus Analogical or Symbolic Versus Connectionist or Neat Versus Scruffy" (in en-US). AI Magazine 12 (2): 34. doi:10.1609/aimag.v12i2.894. ISSN 2371-9621. 
  5. (in en) Word Sense Disambiguation - Algorithms and Applications | Eneko Agirre | Springer. https://www.springer.com/us/book/9781402048081. 
  6. Nancy Ide and Jean Veronis. Introduction to the special issue on word sense disambiguation: the state of the art. Computational Linguistics, 24(1):2-40, 1998
  7. Yampolskiy, Roman (January 2011) (in en). AI-Complete, AI-Hard, or AI-Easy: Classification of Problems in Artificial. https://www.academia.edu/1419272. 
  8. Sycara, Katia; Klusch, Matthias; Widoff, Seth; Lu, Jianguo (1999-03-01). "Dynamic service matchmaking among agents in open information environments". ACM SIGMOD Record 28 (1): 47–53. doi:10.1145/309844.309895. ISSN 0163-5808. 
  9. Oaks, Phillipa; ter Hofstede, Arthur H. M.; Edmond, David (2003), "Capabilities: Describing What Services Can do" (in en), Service-Oriented Computing - ICSOC 2003, Lecture Notes in Computer Science, 2910, Springer Berlin Heidelberg, pp. 1–16, doi:10.1007/978-3-540-24593-3_1, ISBN 9783540206811 
  10. Johannes Fähndrich est First Search Planning of Service Composition Using Incrementally Redefined Context-Dependent Heuristics. In the German Conference Multiagent System Technologies, pages 404-407, Springer Berlin Heidelberg, 2013
  11. Fähndrich, Johannes; Ahrndt, Sebastian; Albayrak, Sahin (2013), "Towards Self-Explaining Agents" (in en), Trends in Practical Applications of Agents and Multiagent Systems, Advances in Intelligent Systems and Computing (Springer International Publishing) 221: pp. 147–154, doi:10.1007/978-3-319-00563-8_18, ISBN 9783319005621 
  12. Goddard, Cliff; Wierzbicka, Anna, eds (1994). Semantic and Lexical Universals: Theory and empirical findings. Amsterdam: Benjamins. 
  13. Fähndrich, Johannes; Ahrndt, Sebastian; Albayrak, Sahin (2014-10-15). "Formal Language Decomposition into Semantic Primes" (in en). Advances in Distributed Computing and Artificial Intelligence Journal 3 (1): 56–73. doi:10.14201/ADCAIJ2014385673. ISSN 2255-2863. http://revistas.usal.es/index.php/2255-2863/article/view/ADCAIJ2014315673. 
  14. "integrating Marker Passing and Problem Solving: A Spreading Activation Approach To Improved Choice in Planning" (in en). 1987-11-01. https://www.crcpress.com/integrating-Marker-Passing-and-Problem-Solving-A-Spreading-Activation-Approach/Hendler/p/book/9780898599824. 
  15. Hirst, Graeme (1987-01-01). Semantic interpretation and the resolution of ambiguity. Cambridge University Press. ISBN 978-0521322034. http://dl.acm.org/citation.cfm?id=30887. 
  16. "Self-Explanation through Semantic Annotation: A Survey" (in en). https://www.researchgate.net/publication/300339119. 
  17. Crestani, Fabio (1997). "Application of Spreading Activation Techniques in Information Retrieval" (in en). Artificial Intelligence Review 11 (6): 453–482. doi:10.1023/A:1006569829653.