The Role of Lexical Ambiguity in Natural Language Processing Systems

Abstract

What are the basic tenets of a system that understands natural languages? What obstacles need to be overcome? One of the problems related to natural language understanding processes is ambiguity. There are two types of ambiguity: Syntactic ambiguity and lexical ambiguity. In syntactic ambiguity, an expression can be decomposed into its constituents in more than one way. In lexical ambiguity, words have more than one meaning. Lexical ambiguity is one of the features that distinguish natural languages from formal languages. There is no lexical ambiguity in a programming language. Is lexical ambiguity an obstacle to modeling natural languages? In other words, does it have adverse effects on artificial intelligence studies? In this work, with reference to contemporary literature, it is stated that lexical ambiguity, especially polysemy, is not a defect but an advantage for cognitive systems.

Keywords

• ambiguity
• polysemy
• natural language processing
• cognitive economy
• the small-world hypothesis

Sözcüksel Muğlaklığın Doğal Dil İşleme Sistemlerindeki Yeri

Abstract

Doğal dilleri anlayabilen bir sistemin temel özellikleri neler olmalıdır? Hangi engellerin aşılması gerekmektedir? Doğal dil anlama süreçleriyle ilgili önemli sorunlardan birisi de muğlaklık olarak görülmektedir. Muğlaklığın iki türünden bahsedilebilir: Sözdizimsel muğlaklık ve sözcüksel muğlaklık. Sözdizimsel muğlaklık durumunda verilen bir ifade bağlama göre birden fazla şekilde sözdizimsel parçalarına ayrılabilmektedir. Muğlaklığın diğer bir türü ise sözcüksel muğlaklıktır. Bu durumda, kelimeler birden fazla anlama sahiptirler. Sözcüksel muğlaklık doğal dilleri biçimsel dillerden ayıran özelliklerden birisidir. Bir programlama dilinin söz dağarcığındaki ifadeler için muğlaklıktan bahsetmek mümkün değildir. Sözcüksel muğlaklık doğal dillerin modellenmesinin önünde bir engel midir? Diğer bir deyişle doğal dillerdeki anlamsal muğlaklığın yapay zekâ çalışmalarını kötü yönde etkilediği söylenebilir mi? Bu çalışmada güncel literatür referans alınarak sözcüksel muğlaklığın özellikle de çokanlamlılığın doğal diller için bilişsel açıdan aslında bir avantaj olduğu ifade edilmektedir.

Keywords

• muğlaklık
• çokanlamlılık
• doğal dil işleme
• bilişsel ekonomi
• küçük dünya hipotezi

References

1. Bar-Hillel, Y. (1964). “A demonstration of the nonfeasibility of fully automatic high quality machine translation." Language and Information: Selected Essays on Their Theory and Application içinde (s. 174-179). Reading, Mass.: Addison-Wesley.
2. Baxter, D. L. (2016). "Hume on Space and Time." P. Russell (Der.), The Oxford Handbook of Hume içinde (s. 173-190). Oxford: Oxford University Press.
3. Bonnen, C. A., ve Flage, D. E. (2000). "Descartes: The Matter of Time." International Studies in Philosophy, 32(4): 1-11.
4. Brugman, C., ve Lakoff, G. (1988). “Cognitive Topology and Lexical Networks." G. W. Steven L. Small ve M. K. Tanenhaus (Der.), Lexical Ambiguity Resolution: Perspectives from Psycholinguistics, Neuropsychology, and Artificial Intelligence içinde (s. 477–508). San, Mateo, CA: Morgan Kaufmann.
5. Chomsky, N. (2002). On Nature and Language. New York: Cambridge University Press.
6. Clark, H. H. (1983). “Making Sense of Nonce Sense.” G. B. D'Arcais, ve R. J. Jarvella (Der.), The Process of Language Understanding içinde (s. 297–331). John Wiley & Sons Ltd.
7. Cohen, J. (1985). “A problem about Ambiguity in Truth-Conditional Semantics.” Analysis, 45: 129–135. de Sola Pool, I., & Kochen, M. (1978). “Contacts and Influence.” Social Networks, 1: 5–51.
8. Descartes, R. (1637/1968). “Discourse on Method and the Meditations.” Çev. F. E. Sutcliffe. London: Penguin Books Ltd.

9. Descartes, R. (1985). Meditations on First Philosophy. J. Cottingham, R. Stoothoff, ve D. Murdoch (Düz.), The Philsophical Wrings of Descartes (Cilt II) içinde, (s. 1-63). Cambridge: Cambridge University Press.
10. Falkum, I. L., ve Vicente, A. (2015). “Polysemy: Current Perspectives and Approaches.” Lingua, 157: 1-16.
11. Fellbaum, C. (2013). “WordNet.” C. A. Chapelle (Der.), The Encyclopedia of Applied Linguistics içinde (s. 707-728). Wiley/Blackwell.
12. Ferrer i Cancho, R., ve Solé, R. V. (2003). “Least Effort and the Origins of Scaling in Human Language.” Proceedings of the National Academy of Sciences of the United States of America, 100(3): 788–791.
13. Garrett, D. (1981). “Hume's Self-Doubts about Personal Identity.” The Philosophical Review, 90(3): 337-358.
14. Garrett, D. (2008). “Hume’s Theory of Ideas." E. S. Radcliffe (Der.), A Companion to Hume içinde (s. 41-57). Oxford: Blackwell Publishing.
15. Giles, J. (1993). “The No-Self Theory: Hume, Buddhism, and Personal Identity.” Philosophy East and West, 43(2): 175-200.
16. Goodman, N. (1968). Languages of Art: An Approach to a Theory of Symbols. Hackett publishing.
17. Harris, C. L. (1994). “Coarse Coding and the Lexicon.” C. Fuchs ve B. Victorri (Der.), Continuity in Linguistic Semantics içinde (s. 205–229). Amsterdam: John Benjamins Publishing Company.
18. Hume, D. (1960). A Treatise of Human Nature. Düz. L. A. Selby-Biggie. Oxford: The Calderon Press.
19. Locke, J. (1999). Essay Concerning Human Understanding. Pennsylvania: Pennsylvania State University Press.
20. Melamed, Y. Y. (2014). “What is Time?” A. Garrett (Der.), The Routledge Companion to Eighteenth Century Philosophy içinde (s. 232-244). London & New York: Routledge.
21. Mermin, N. D. (2009). “What's Bad about This Habit.” Physics Today 62: 8-9.
22. Milgram, S. (1967). “The Small World Problem.” Psychology today, 2: 60–67.
23. Morrison, P. (1978). “Kant, Husserl and Heidegger on Time and Unity of 'Consciousness'.” Philosophical and Phenomenelogical Research, 39(2): 182-198.
24. Norvig, P. ve Lakoff, G. (1987). “Taking: A Study in Lexical Network Theory.” Annual Meeting of the Berkeley Linguistics Society, 13: 195–206.
25. Penelhum, T. M. (1976). “The Self in Hume's Philosophy.” The Soutwestern Journal of Philosophy, 7(2): 9-23.
26. Peters, M. E., Ammar, W., Bhagavatula, C., ve Power, R. (2017). “Semi-Supervised Sequence Tagging with Bidirectional Language Models.” Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Volume 1: Long Papers içinde (s. 1756–1765). Vancouver, Canada. Association for Computational Linguistics.
27. Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., ve Zettlemoyer, L. (2018). “Deep Contextualized Word Representations.” Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1: Long Papers içinde (s. 2227–2237). New Orleans, Louisiana. Association for Computational Linguistics.
28. Piantadosi, S. T., Tily, H., ve Gibson, E. (2012). “The Communicative Function of Ambiguity in Language.” Cognition, 122: 280–291.
29. Pitson, A. E. (2002). Hume's Philosophy of the Self. London & New York: Routledge.
30. Pustejovsky, J. (1996). The Generative Lexicon. MIT Press.
31. Rayo, A. (2013). “A Plea for Semantic Localism.” Noûs, 47: 647–679.
32. Shannon, C. E. (1948). “A Mathematical Theory of Communication.” The Bell System Technical Journal, 27: 379-423.
33. Solé, R. V. ve Seoane, L. F. (2015). “Ambiguity in Language Networks.” The Linguistic Review, 32: 5–35.
34. Solé, R. V., Corominas-Murtra, B., Valverde, S. ve Steels, L. (2010). “Language Networks: Their Structure, Function, and Evolution.” Complexity, 15: 20–26.
35. Srinivasan, M. ve Rabagliati, H. (2015). “How Concepts and Conventions Structure the Lexicon: Cross-Linguistic Evidence from Polysemy.” Lingua, 157: 124–152.
36. Taylor, J. R. (2003). “Polysemy's Paradoxes.” Language Sciences, 25: 637-655. https://doi.org/10.1016/S0388-0001(03)00031-7
37. Turing, A. M. (1950). “Computing Machinery and Intelligence.” Mind, 59: 433–60. DOI: 10.1093/mind/LIX.236.433
38. Wasow, T. (2015). “Ambiguity Avoidance is Overrated.” Susanne Winkler (Der.), Ambiguity: Language and Communication içinde (s. 29-48). De Gruyter.
39. Wasow, T., Perfors, A. ve Beaver, D. (2005). “The Puzzle of Ambiguity.” C. Orhan Orgun ve Peter Sells (Der.), Morphology and the Web of Grammar: Essays in Memory of Steven G. Lapointe içinde (s. 265–282). CSLI Publications.
40. Waxman, W. (2008). “Hume and the Origin of Our Ideas of Space and Time.” E. S. Radcliffe (Der.), A Companion to Hume içinde (s. 72-88). Oxford: Blackwell Publishing.
41. Zipf, G. K. (1949). Human Behavior and the Principle of Least Effort: An Introduction to Human Ecology. New York: Hafner Publishing Company.