Inteligência Artificial e os rumos do processamento do português brasileiro
DOI:
https://doi.org/10.1590/s0103-4014.2021.35101.005Palavras-chave:
Processamento de língua natural, Redes neurais, Contexto linguístico, Português brasileiroResumo
Neste artigo apresentamos um posicionamento sobre a área de processamento de língua natural em português, seus desenvolvimentos desde o princípio até a explosão de aplicações modernas baseadas em aprendizado de máquina. Exploramos os desafios que a área necessita enfrentar no momento, tanto de natureza técnica quanto de natureza ética e moral, e concluímos com a inabalável associação do processamento de língua natural com os estudos linguísticos.
Downloads
Referências
AHO, A. V. et al. Compilers: principles, techniques, and tools. New York: Addison
-Wesley Longman Publishing Co., Inc. 1986.
AIZERMAN, M. A. et al. Theoretical Foundations of the Potential Function Method
in Pattern Recognition Learning. Automation and Remote Control, n.25, p.821-37,
ANDERSON, D.; BURNHAM, K. Model Selection and Multi-Model Inference. 2.ed.
New York: Springer, 2004.
BAHDANAU, D. et al. Neural Machine Translation by Jointly Learning to Align and
Translate. 2016. Disponível em: <http://arxiv.org/abs/1409.0473>.
BARTLETT, P. L. et al. Almost Linear Vc-Dimension Bounds for Piecewise Polynomial
Networks. Neural Comput., v.10, n.8, p.2159-73, 1998. Disponível em:
uni-trier.de/db/journals/neco/neco10.html#BartlettMM98>.
BENDER, E. M.; KOLLER, A. Climbing Towards NLU: On Meaning, Form, and
Understanding in the Age of Data. In: PROCEEDINGS OF THE 58TH ANNUAL
MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS,
p.5185-98. 2020. Online: Association for Computational Linguistics. Disponível em:
<https://doi.org/10.18653/v1/2020.acl-main.463>.
BENTHEM, J. van. Language in Action. s. l.: MIT Press, 1995.
BLEI, D. M. Latent Dirichlet Allocation. J. Mach. Learn. Res., v.3, p.993-1022, 2003.
Disponível em: <https://doi.org/http://dx.doi.org/10.1162/jmlr.2003.3.4-5.993>.
BROWN, T. B. et al. Language Models Are Few-Shot Learners. 2020. Disponível em:
<http://arxiv.org/abs/2005.14165>.
BUCHANAN, B. G. A (Very) Brief History of Artificial Intelligence. AI Magazine,
v.26, n.4, p.53, 2005.
CARPENTER, B. Type-Logical Semantics. Cambridge: The MIT Press, 1997.
CHARNIAK, E. Statistical Language Learning. Cambridge: The MIT Press, 1993.
CHOMSKY, N. Aspects of the Theory of Syntax. Cambridge: The MIT Press, 1965.
Disponível em: <http://www.amazon.com/Aspects-Theory-Syntax-Noam-Chomsky/
dp/0262530074>.
CLARK, A.; LAPPIN, S. Unsupervised Learning and Grammar Induction. The Handbook of Computational Linguistics and Natural Language Processing, n.57, 2010.
DAMERAU, F. J. Markov Models and Linguistic Theory. De Gruyter Mouton, 1971.
Disponível em: <https://doi.org/doi:10.1515/9783110908589>.
DEVLIN, J. et al. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. 2019. Disponível em: <http://arxiv.org/abs/1810.04805>.
DWIVEDI, V. P. et al. Benchmarking Graph Neural Networks. 2020. Disponível em:
<http://arxiv.org/abs/2003.00982>.
HARRELL, F. E. Regression Modeling Strategies: With Applications to Linear Models,
Logistic Regression, and Survival Analysis. Springer, 2001.
HOCHREITER, S. et al. Gradient Flow in Recurrent Nets: The Difficulty of Learning
Long-Term Dependencies. In KREMER, S. C.; KOLEN, J. F. (Ed.) A Field Guide to
Dynamical Recurrent Neural Networks. s.l.: IEEE Press, 2001.
HOPCROFT, J. E.; ULLMAN, J. D. Introduction to Automata Theory, Languages,
and Computation. s. l.: Addison-Wesley Publishing Company, 1979.
HORNIK, K. et al. Multilayer Feedforward Networks Are Universal Approximators.
Neural Networks, v.2, n.5, p.359-66, 1989. Disponível em: <https://doi.org/http://
dx.doi.org/10.1016/0893-6080(89)90020-8>.
JURAFSKY, D.; MARTIN, J. H. Speech and Language Processing: An Introduction
to Natural Language Processing, Computational Linguistics, and Speech Recognition.
New York: Prentice Hall PTR, 2000.
KOEHN, P. Statistical Machine Translation. s. l.: Cambridge University Press, 2009.
Disponível em: <https://doi.org/10.1017/CBO9780511815829>.
LAMBEK, J. The Mathematics of Sentence Structure. American Mathematical Monthly, v.65, p.154-69, 1958.
LIU, Y. et al. RoBERTa: A Robustly Optimized Bert Pretraining Approach, 2019.
Disponível em: <http://arxiv.org/abs/1907.11692>.
LUONG, M.-T. et al. Effective Approaches to Attention-Based Neural Machine Translation. 2015. Disponível em: <http://arxiv.org/abs/1508.04025>.
MAASS, W. et al. A Comparison of the Computational Power of Sigmoid and Boolean
Threshold Circuits. In: ROYCHOWDHURY, V. et al. (Ed.) Theoretical Advances in Neural Computation and Learning. Boston, MA: Springer US, 1994. p.127-50. Disponível em: <https://doi.org/10.1007/978-1-4615-2696-4_4.>
MANNING, C. D.; SCHÜTZE, H. Foundations of Statistical Natural Language Processing. Cambridge, MA: MIT Press, 1999.
MARTIN, L. et al. CamemBERT: A Tasty French Language Model. In: PROCEEDINGS OF THE 58TH ANNUAL MEETING OF THE ASSOCIATION FOR
COMPUTATIONAL LINGUISTICS, 2020. p.7203-19. Dispnível em:
org/10.18653/v1/2020.acl-main.645>.
MIKOLOV, T. et al. Efficient Estimation of Word Representations in Vector Space.
Disponível em: <http://arxiv.org/abs/1301.3781>.
MIKOLOV, T. et al. Distributed Representations of Words and Phrases and Their Compositionality. In: BURGES, C. J. C et al (Ed.) Advances in Neural Information Processing Systems. Curran Associates, Inc., 2016. v.26. Disponível em:
neurips.cc/paper/2013/file/9aa42b31882ec039965f3c4923ce901b-Paper.pdf>.
MINSKY, M.; PAPERT, S. Perceptrons. Cambridge, MA: The MIT Press, 1969.
MOORTGAT, M. Categorial Type Logics. In: BENTHEM, A. van; MEULEN, A. T,
(Ed.) Handbook of Logic and Language. Elsevier North-Holland: The MIT Press. 1997.
NEWELL, A.; SIMON, H. A. GPS, a Program That Simulates Human Thought. In:
FEIGENBAUM, E. A.; FELDMAN, J. (Ed.) Computers and Thought. s. l.: McGraw-
-Hill, 1963. p.279-93.
NOVIKOFF, A. B. On Convergence Proofs on Perceptrons. In: PROCEEDINGS OF
THE SYMPOSIUM ON THE MATHEMATICAL THEORY OF AUTOMATA, 12,
p.615-22. Polytechnic Institute of Brooklyn, New York, 1962.
OCH, F. J.; NEY, H. 2002. Discriminative Training and Maximum Entropy Models
for Statistical Machine Translation. In: PROCEEDINGS OF THE 40TH ANNUAL
MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS,
p.295-302. 2002.
PAPADIMITRIOU, H. Computational Complexity. s.l.: Addison-Wesley, 1994.
PEREIRA, F. C. N.; SHIEBER, S. M. Prolog and Natural-Language Analysis. s.l.:
Center for the Study of Language; Information, 1987.
PIRES, T. et al. How Multilingual Is Multilingual Bert?. 2019. Disponível em:
arxiv.org/abs/1906.01502>.
ROSENBLATT, F. The perceptron: A probabilistic model for information storage and
organization in the brain. Psychological Review, v.65, n.6, p.386-408, 1958. Disponível
em: <https://doi.org/10.1037/h0042519>.
ROSENBLATT, F. Principles of Neurodynamics. New York: Spartan, 1962.
RUMELHART, D. E. et al. Learning Internal Representations by Error Propagation.
In: RUMELHART, D. E.; MCCLELLAND, J. L. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Cambridge, MA: The MIT Press, 1986a.
v.1: Foundations, p.318-62.
RUMELHART, D. E.. Learning Representations by Back-Propagating Errors. Nature, v.323, n.6088,
p.533-36, 1986b. Disponível em: <http://dx.doi.org/10.1038/323533a0>.
SALVATORE, F. et al. A Logical-Based Corpus for Cross-Lingual Evaluation. In: Deep
Learning for Low-Resource Nlp Workshop at Emnlp 2019. 2019.
SANH, V. DistilBERT, a Distilled Version of Bert: Smaller, Faster, Cheaper and Lighter. 2020. Disponível em: <http://arxiv.org/abs/1910.01108>.
SCARSELLI, F. et al. The Graph Neural Network Model. IEEE Transactions on Neural Networks, v.20, n.1, p.61-80, 2009. Disponível em: <https://doi.org/10.1109/
TNN.2008.2005605>.
SOUZA, F. et al. BERTimbau: Pretrained Bert Models for Brazilian Portuguese. In:
CERRI, R.; PRATI, R. C. (Ed.) Intelligent Systems. Cham: Springer International Publishing, 2020. p.403-17.
SUTSKEVER, I. et al. Sequence to Sequence Learning with Neural Networks. 2014.
Disponível em: <http://arxiv.org/abs/1409.3215>.
VAPNIK, V. N. The Nature of Statistical Learning Theory. New York: Springer-Verlag
Inc., 1995.
VASWANI, A. et al. Attention Is All You Need. 2017. Disponível em:
org/abs/1706.03762>.
WAGNER FILHO, J. A. et al. The BrWaC Corpus: A New Open Resource for Brazilian
Portuguese. In: PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018).
Miyazaki, Japan: European Language Resources Association (ELRA). 2018. Disponível
em: <https://www.aclweb.org/anthology/L18-1686>.
YANG, Z. et al. XLNet: Generalized Autoregressive Pretraining for Language Understanding. 2020. Disponível em: <http://arxiv.org/abs/1906.08237>.
Publicado
Edição
Seção
Licença
Copyright (c) 2021 Marcelo Finger
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial 4.0 International License.
Estudos Avançados não celebra contrato de cessão de direitos autorais com seus colaboradores, razão pela qual não detém os direitos autorais dos artigos publicados. Os interessados em reproduzir artigos publicados na revista devem necessariamente obter o consentimento do autor e atribuir devidamente os créditos ao periódico.
