The distributed representation of symbols is one of the key technologies...
A limited amount of studies investigates the role of model-agnostic
adve...
A natural language database interface (NLDB) can democratize data-driven...
Contextual word-representations became a standard in modern natural lang...
Written language contains stylistic cues that can be exploited to
automa...
Recent work has highlighted the advantage of jointly learning grounded
s...
Lemmatization of standard languages is concerned with (i) abstracting ov...
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...
We introduce TextWorld, a sandbox learning environment for the training ...
Traditionally, Referring Expression Generation (REG) models first decide...
The bulk of research in the area of speech processing concerns itself wi...
We introduce FigureQA, a visual reasoning corpus of over one million
que...
We decompose multimodal translation into two sub-tasks: learning to tran...
We present novel methods for analyzing the activation patterns of RNNs f...