Understanding which information is encoded in deep models of spoken and
...
Human language is firstly spoken and only secondarily written.
Text, h...
Self-attention weights and their transformed variants have been the main...
Attempts to computationally simulate the acquisition of spoken language ...
A limited amount of studies investigates the role of model-agnostic
adve...
We present the visually-grounded language modelling track that was intro...
The distributed and continuous representations used by neural networks a...
This survey provides an overview of the evolution of visually grounded m...
Written language contains stylistic cues that can be exploited to
automa...
Visually-grounded models of spoken language understanding extract semant...
Speech directed to children differs from adult-directed speech in lingui...
Given the fast development of analysis techniques for NLP and speech
pro...
Recent work has highlighted the advantage of jointly learning grounded
s...
Analysis methods which enable us to better understand the representation...
The EMNLP 2018 workshop BlackboxNLP was dedicated to resources and techn...
A widespread approach to processing spoken language is to first automati...
Recent work has shown how to learn better visual-semantic embeddings by
...
Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art...
The task of obfuscating writing style using sequence models has previous...
The bulk of research in the area of speech processing concerns itself wi...
We study the representation and encoding of phonemes in a recurrent neur...
We present a visually grounded model of speech perception which projects...
We present a model of visually-grounded language learning based on stack...
We present novel methods for analyzing the activation patterns of RNNs f...