The Future of Computational Linguistics: On Beyond Alchemy

被引:11
作者
Church, Kenneth [1 ]
Liberman, Mark [2 ]
机构
[1] Baidu Res, Sunnyvale, CA USA
[2] Univ Penn, Philadelphia, PA 19104 USA
来源
FRONTIERS IN ARTIFICIAL INTELLIGENCE | 2021年 / 4卷
关键词
empiricism; rationalism; deep nets; logic; probability; connectionism; computational linguistics; alchemy;
D O I
10.3389/frai.2021.625341
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Over the decades, fashions in Computational Linguistics have changed again and again, with major shifts in motivations, methods and applications. When digital computers first appeared, linguistic analysis adopted the new methods of information theory, which accorded well with the ideas that dominated psychology and philosophy. Then came formal language theory and the idea of AI as applied logic, in sync with the development of cognitive science. That was followed by a revival of 1950s-style empiricism-AI as applied statistics-which in turn was followed by the age of deep nets. There are signs that the climate is changing again, and we offer some thoughts about paths forward, especially for younger researchers who will soon be the leaders.
引用
收藏
页数:18
相关论文
共 98 条
[41]  
Jelinek F., 1990, Readings in speech recognition, P450, DOI 10.1016/B978-0-08-051584-7.50045-0
[42]   NATIONAL-SCIENCE-FOUNDATION AND DEBATE OVER POSTWAR RESEARCH POLICY, 1942-1945 - POLITICAL INTERPRETATION OF SCIENCE - ENDLESS FRONTIER [J].
KEVLES, DJ .
ISIS, 1977, 68 (241) :5-26
[43]  
Kiparsky P., 2015, MORE WORDS FESTSCHRI, V53
[44]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[45]  
Kuhn T., 1962, The Structure of Scientific Revolutions
[46]   The Omniglot challenge: a 3-year progress report [J].
Lake, Brenden M. ;
Salakhutdinov, Ruslan ;
Tenenbaum, Joshua B. .
CURRENT OPINION IN BEHAVIORAL SCIENCES, 2019, 29 :97-104
[47]   Human-level concept learning through probabilistic program induction [J].
Lake, Brenden M. ;
Salakhutdinov, Ruslan ;
Tenenbaum, Joshua B. .
SCIENCE, 2015, 350 (6266) :1332-1338
[48]  
Lake Brenden M., 2017, INT C MACH LEARN
[49]   Gradient-based learning applied to document recognition [J].
Lecun, Y ;
Bottou, L ;
Bengio, Y ;
Haffner, P .
PROCEEDINGS OF THE IEEE, 1998, 86 (11) :2278-2324
[50]   Deep learning [J].
LeCun, Yann ;
Bengio, Yoshua ;
Hinton, Geoffrey .
NATURE, 2015, 521 (7553) :436-444