Page: 1... 201 202 203 204 205
Hits 4.081 – 4.089 of 4.089
4081 |
Singing voice phoneme segmentation by hierarchically inferring syllable and phoneme onset positions
|
|
|
|
BASE
|
|
Show details
|
|
4083 |
SignON: Bridging the gap between sign and spoken languages
|
|
|
|
BASE
|
|
Show details
|
|
4085 |
Multiplicative and additive modulation of neuronal tuning with population activity affects encoded information
|
|
|
|
BASE
|
|
Show details
|
|
4086 |
How to represent a word and predict it, too: improving tied architectures for language modelling
|
|
|
|
BASE
|
|
Show details
|
|
4088 |
Linguistic generalization and compositionality in modern artificial neural networks.
|
|
|
|
Abstract:
In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks. Given the high productivity of language, these models must possess e ective generalization abilities. It is widely assumed that humans handle linguistic productivity by means of algebraic compositional rules: Are deep networks similarly compositional? After reviewing the main innovations characterizing current deep language processing networks, I discuss a set of studies suggesting that deep networks are capable of subtle grammar-dependent generalizations, but also that they do not rely on systematic compositional rules. I argue that the intriguing behaviour of these devices (still awaiting a full understanding) should be of interest to linguists and cognitive scientists, as it o ers a new perspective on possible computational strategies to deal with linguistic productivity beyond rule-based compositionality, and it might lead to new insights into the less systematic generalization patterns that also appear in natural language.
|
|
Keyword:
Artificial neural networks; Compositionality; Deep learning; Linguistic productivity
|
|
URL: https://doi.org/10.1098/rstb.2019.0307 http://hdl.handle.net/10230/43459
|
|
BASE
|
|
Hide details
|
|
4089 |
LaSTUS/TALN+INCO @ CL-SciSumm 2018 - Using regression and convolutions for cross-document semantic linking and summarization of scholarly literature
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1... 201 202 203 204 205
|
|