142 |
Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate ...
|
|
|
|
Abstract:
Can advances in NLP help advance cognitive modeling? We examine the role of artificial neural networks, the current state of the art in many common NLP tasks, by returning to a classic case study. In 1986, Rumelhart and McClelland famously introduced a neural architecture that learned to transduce English verb stems to their past tense forms. Shortly thereafter, Pinker & Prince (1988) presented a comprehensive rebuttal of many of Rumelhart and McClelland's claims. Much of the force of their attack centered on the empirical inadequacy of the Rumelhart and McClelland (1986) model. Today, however, that model is severely outmoded. We show that the Encoder-Decoder network architectures used in modern NLP systems obviate most of Pinker and Prince's criticisms without requiring any simplication of the past tense mapping problem. We suggest that the empirical performance of modern networks warrants a re-examination of their utility in linguistic and cognitive modeling. ... : TACL 2018 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1807.04783 https://dx.doi.org/10.48550/arxiv.1807.04783
|
|
BASE
|
|
Hide details
|
|
144 |
Unsupervised Disambiguation of Syncretism in Inflected Lexicons ...
|
|
|
|
BASE
|
|
Show details
|
|
145 |
A Discriminative Latent-Variable Model for Bilingual Lexicon Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
146 |
A Discriminative Latent-Variable Model for Bilingual Lexicon Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
147 |
A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
|
|
|
|
BASE
|
|
Show details
|
|
148 |
A Structured Variational Autoencoder for Contextual Morphological Inflection
|
|
|
|
BASE
|
|
Show details
|
|
149 |
Quantifying the Trade-off Between Two Types of Morphological Complexity
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2018)
|
|
BASE
|
|
Show details
|
|
151 |
Probabilistic Typology: Deep Generative Models of Vowel Inventories ...
|
|
|
|
BASE
|
|
Show details
|
|
152 |
One-Shot Neural Cross-Lingual Transfer for Paradigm Completion ...
|
|
|
|
BASE
|
|
Show details
|
|
153 |
Cross-lingual, Character-Level Neural Morphological Tagging ...
|
|
|
|
BASE
|
|
Show details
|
|
154 |
Probabilistic Typology: Deep Generative Models of Vowel Inventories ...
|
|
|
|
BASE
|
|
Show details
|
|
155 |
Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles ...
|
|
|
|
BASE
|
|
Show details
|
|
158 |
Probabilistic Typology: Deep Generative Models of Vowel Inventories
|
|
Eisner, Jason; Cotterell, Ryan. - : Association for Computational Linguistics, 2017. : Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2017
|
|
BASE
|
|
Show details
|
|
159 |
Weighting Finite-State Transductions With Neural Context
|
|
Eisner, Jason; Cotterell, Ryan; Rastogi, Pushpendre. - : Association for Computational Linguistics, 2016. : Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016
|
|
BASE
|
|
Show details
|
|
160 |
A Joint Model of Orthography and Morphological Segmentation
|
|
Cotterell, Ryan; Vieira, Tim; Schütze, Hinrich. - : Association for Computational Linguistics, 2016. : Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016
|
|
BASE
|
|
Show details
|
|
|
|