2 |
Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Discrete representations in neural models of spoken language ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Analyzing analytical methods: The case of phonology in neural models of spoken language ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Learning to Understand Child-directed and Adult-directed Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Bootstrapping Disjoint Datasets for Multilingual Multimodal Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
On the difficulty of a distributional semantics of spoken language
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2019)
|
|
BASE
|
|
Show details
|
|
9 |
Lessons learned in multilingual grounded language learning ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
On the difficulty of a distributional semantics of spoken language ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Encoding of phonology in a recurrent neural model of grounded speech ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Rnn Models For Representation Of Linguistic Form And Function In Recurrent Neural Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Rnn Models For Representation Of Linguistic Form And Function In Recurrent Neural Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Representations of language in a model of visually grounded speech signal ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning ...
|
|
|
|
Abstract:
We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles that faced by human language learners who need to discover both structure and meaning from noisy and ambiguous data across modalities. We show that our model indeed learns to predict features of the visual context given phonetically transcribed image descriptions, and show that it represents linguistic information in a hierarchy of levels: lower layers in the stack are comparatively more sensitive to form, whereas higher layers are more sensitive to meaning. ... : Accepted at COLING 2016 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1610.03342 https://arxiv.org/abs/1610.03342
|
|
BASE
|
|
Hide details
|
|
17 |
Representation of linguistic form and function in recurrent neural networks ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Elephant: Sequence Labeling for Word and Sentence Segmentation
|
|
|
|
In: EMNLP 2013 ; https://hal.archives-ouvertes.fr/hal-01344500 ; EMNLP 2013, Oct 2013, Seattle, United States (2013)
|
|
BASE
|
|
Show details
|
|
20 |
Elephant: Sequence labeling for word and sentence segmentation
|
|
|
|
BASE
|
|
Show details
|
|
|
|