The Status Quo of the English Past-Tense Debate

다국어 초록 (Multilingual Abstract)

This paper described phenomena related to the past tense in English, summarized the theories and empirical evidence to explain these phenomena. It aimed to present implications for the past tense and similar language phenomena in current deep learning models, such as ChatGPT, a modern large language model(LLM). The discussion related to the past tense in English dates back to when a special article called "The Past-Tense Debate" was published in Trends in Cognitive Sciences in 2002. As a result, seemingly simple language phenomena gained the interest of researchers in various fields such as linguistics, psychology, and computer science. Steven Pinker and Michael Ullman wrote a paper titled "The past and future of the past tense," to which James McClelland and Karalyn Patterson responded with a paper stating, "Words or Rules cannot exploit the regularity in exceptions." McClelland and Patterson published a paper titled "Rules or connections in past-tense inflections: what does the evidence rule out?" and Pinker and Ullman countered with "Combination and structure, not gradedness, is the issue." At this point, twenty years later, in 2023, ChatGPT, a neural network-based AI system, has attracted global attention. In this paper, we examine past tense theories and explore whether recent neural networks like ChatGPT resolve the past tense debate or if the issues raised in that debate are still relevant in the current era of artificial intelligence.

참고문헌 (Reference)

1 Adam Albright, "analogy in english past tenses : A computational/experimental study" 90 (90): 119-161, 2003

2 Pinker, Steven, "Words and Rules: The Ingredients of Language" HarperCollins 1999

3 Kim, J. J., "Why no mere mortal has ever flown out to the center field" 15 : 173-218, 1991

4 Bybee, Joan, "Three frequency effects in syntax" Berkeley Linguistics Society 378-388, 1997

5 Nicoladis, E., "The role of type and token frequency in using past tense morphemes correctly" 10 (10): 237254-, 2007

6 Pinker, Steven, "The past and future of the past tense" 6 : 456-463, 2002

7 Ullman, M. T, "The declarative/procedural model of lexicon and grammar" 30 : 37-69, 2001

8 Berko, Jean, "The child's learning of English morphology" 14 : 150-177, 1958

9 Chomsky, Noam, "The Sound Pattern of English" MIT Press 1968

10 Squire, L. R., "The New Cognitive Neurosciences" MIT Press 765-780, 2000

11 Baayen, R. Harald, "The CELEX lexical data base on CD-ROM"

12 Pierrehumbert, Janet, "Stochastic phonology" 5 : 195-207, 2001

13 McClelland, James L, "Rules or connections in past-tense inflections: what does the evidence rule out?" 6 : 465-472, 2002

14 Bybee, Joan, "Regular morphology and the lexicon" 10 : 425-455, 1995

15 Kirov, Christoand Ryan Cotterell, "Recurrent neu- ral networks in linguistic theory:Revisiting pinker and prince(1988) and the past tense debate" 6 : 651-665, 1988

16 Seidenberg, Mark S., "Quasiregularity and its discontents: The legacy of the past tense debate" 38 : 1190-1228, 2014

17 Bybee, Joan, "Phonology and language use" Cambridge University Press 2003

18 Marcus, G.F, "Overregularization in language acquisition" 57 : 1-165, 1992

19 Rumelhart, David E., "On learning the past tenses of English verbs" MIT Press 2 : 1986

20 Pinker, Steven, "On language and connectionism: Analysis of a parallel distributed processing model of language acquisition" 28 (28): 73193-, 1988

21 Ma, Xiaomeng, "How do we get there? Evaluating transformer neural networks as cognitive models for English past inflection" 1101-1114, 2022

22 Prasada, S., "Generalization of regular and irregular morphological patterns" 8 : 1-56, 1993

23 Redmond, Sean M., "Detection of irregular verb violations by children with and without SLI" 44 : 655-669, 2001

24 Corkery, Maria, "Are we there yet? encoder-decoder neural networks as cognitive models of english past tense inflection" 3868-3877, 2019

25 Brown, Roger, "A First Language" Harvard University Press 1973