언어 능력과 자연어 처리: 자연인가 경험인가?
Language competence and natural language processing: Nature or nurture?
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This study reviews two opposing theories regarding human language competence, i.e. the logical nativism vs. empiricism, which is reminiscent of the so-called ‘nature vs. nurture’ dispute originating from Plato’s dialogues. Generative grammar is the representative linguistic theory that embodies the idea of logical nativism, whereas Constructivist theory is the typical experience-based linguistic approach. Connectionist model (deep learning), the leading methodology of current NLP(natural language processing), is reconsidered with respect to the two theories of language competence aforementioned and the empirical nature of deep learning devise is confirmed. By reviewing possibilities and limitations of integration of the empirical approach of connectionism and the rule-based approach of theoretical linguistics discussed by Pater (2019) and others, it is concluded that a hybrid approach is in need. Two additional factors supporting the hybrid approach are provided, one for a proper explanation of the difference between native language acquisition and foreign language acquisition and the other from the empirical nature incorporated in Montague semantics which is fundamentally a rule-based linguistic theory.
Abstract
This study reviews two opposing theories regarding human language competence, i.e. the logical nativism vs. empiricism, which is reminiscent of the so-called ‘nature vs. nurture’ dispute originating from Plato’s dialogues. Generative grammar is the representative linguistic theory that embodies the idea of logical nativism, whereas Constructivist theory is the typical experience-based linguistic approach. Connectionist model (deep learning), the leading methodology of current NLP(natural language processing), is reconsidered with respect to the two theories of language competence aforementioned and the empirical nature of deep learning devise is confirmed. By reviewing possibilities and limitations of integration of the empirical approach of connectionism and the rule-based approach of theoretical linguistics discussed by Pater (2019) and others, it is concluded that a hybrid approach is in need. Two additional factors supporting the hybrid approach are provided, one for a proper explanation of the difference between native language acquisition and foreign language acquisition and the other from the empirical nature incorporated in Montague semantics which is fundamentally a rule-based linguistic theory.
참고문헌 (40)
- Berwick Robert C., "Why only us? Language and evolution" (2016), MIT Press
- Bloom, L., "Why not Pivot Grammar?", Journal of Speech and Hearing Disorders, 36, pp.40~50 (1971)
- Brandom, R., "Inferentialism and Some of its Challenges", Philosophy and Phenomelogical Research, 74(3), pp.651~676 (2007)
- Brent I., "No integration without structured representations: Response to Pater", Language, 95(1), pp.75~86 (2019)
- Chaabouni, Rahma, "Learning weakly supervised multimodal phoneme embeddings", Proceedings of INTERSPEECH, pp.2218~2222 (2017)
- Chomsky, Noam, "Syntactic Structures" (1957), Mouton
- Chomsky, Noam, "Problems of Knowledge and Freedom" (1971), Pantheon Books
- Chomsky, Noam, "Lectures on Government and Binding" (1981), Foris
- Chomsky, Noam, "The Minimalist Program" (1995), MIT Press
- Crain, S, "The Emergence of Meaning" (2012), Cambridge University Press
- Croft, W, "Radical Construction Grammar : Syntactic Theory in Typological Perspective" (2001), Oxford University Press
- Dummett, M., "Truth and Other Enigmas" (1978), Harvard University Press
- Dunbar Ewan, "Generative grammar, neural networks, and the implementational mapping problem: Response to Pater", Language, 95(1), pp.e87~e98 (2019)
- Dunbar, Ewan, "Quantitative Methods for Comparing Featural Representations", Proceedings of the 18th International Congress of Phonetic Sciences (ICPhS) (2015)
- Dyer, Chris, "Recurrent Neural Network Grammars", Proceedings of NAACL-HLT, pp.199~209 (2016)
- Jeffrey L. Elman, "Distributed Representations, Simple Recurrent Networks, and Grammatical Structure", Machine Learning, 7(2–3), pp.195~225 (1991), Springer Science and Business Media LLC[DOI]
- Gladkova, Anna, "Analogy-based Detection of Morphological and Semantic Relations with Word Embeddings: What Works and What doesn’t", Proceedings of the NAACL Student Research Workshop, pp.8~15 (2016)
- Goldberg, A. E., "Constructions : A Construction Grammar Approach to Argument Structure" (1995), University of Chicago Press
- Goodkind, Adam, "Predictive Power of Word Surprisal for Reading Times is a Linear Function of Language Model Quality", Proceedings of the 8th Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2018), pp.10~18 (2018)
- Langacker R. W., "Foundations of Cognitive Grammar" (1991), Standford University Press
- Lewis, John D., "Learnability and the Statistical Structure of Language: Poverty of Stimulus Arguments Revisited", Proceedings of the Boston University Conference on Language Development (BUCLD), 26, pp.359~370 (2001)
- Linzen Tal, "What can Linguistics and Deep Learning Contribute to each other? Response to Pater", Language, 95(1), pp.e41~e74 (2019)[DOI]
- Linzen, Tal, "Quantificational Features in Distributional Word Representations", Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics (*SEM 2016), pp.1~11 (2016)
- McCoy, R. Thomas, "Revisiting the Poverty of the Stimulus: Hierarchical Generalization without a Hierarchical Bias in Recurrent Neural Networks", Proceedings of the 40th annual conference of the Cognitive Science Society (CogSci 2018), pp.2093~2098 (2018)
- Marvin, Rebecca, "Targeted Syntactic Evaluation of Language Models", Proceedings of the 2018 conference on Empirical Methods in Natural Language Processing, pp.1192~1202 (2018)
- "Efficient estimation of word representations in vector space" (2013)[URL]
- Minsky, Marvin, "Perceptrons: An introduction to computational geometry" (1988), MIT Press
- Montague, R., "Formal Philosophy : Selected Papers of Richard Montague" (1974), Yale University Press
- Pater, Joe, "Generative Linguistics and Neural Networks at 60: Foundation, Friction, and Fusion", Language, 95(1), pp.e41~e74 (2019)
- Jordan B. Pollack, "Recursive distributed representations", Artificial Intelligence, 46(1-2), pp.77~105 (1990), Elsevier BV[DOI]
- Pullum, G, "Empirical Assessment of the Stimulus Poverty Argument", The Linguistic Review, 19, pp.9~50 (2002)
- Quine, W.V.O., "The Philosophy of Logic" (1986), Harvard University Press
- Brian Roark, "Probabilistic Top-Down Parsing and Language Modeling", Computational Linguistics, 27(2), pp.249~276 (2001), MIT Press - Journals[DOI]
- The Perceptron: A Perceiving and Recognizing Automaton (Project PARA), "Rosenblatt, Frank", Cornell Aeronautical Laboratory, ~, pp.Report 85-460-1 (1957)
- F. Rosenblatt, "The perceptron: A probabilistic model for information storage and organization in the brain.", Psychological Review, 65(6), pp.386~408 (1958), American Psychological Association (APA)[DOI]
- Rosenblatt, Frank, "Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms" (1962), Spartan Books
- Rumelhart, David E., "On learning the past tenses of English verbs. Parallel distributed processing: Explorations in the microstructures of cognition, vol. 2", pp.216~271 (1986), MIT Press
- van Schijndel, Marten, "A Model of Language Processing as Hierarchic Wequential Prediction", Topics in Cognitive Science, 5(3), pp.522~540 (2013)[DOI]