Curriculum learning (CL) posits that machine learning models – similar t...
At the staggering pace with which the capabilities of large language mod...
In natural language, referencing objects at different levels of specific...
Moving towards human-like linguistic performance is often argued to requ...
In this paper, we propose to study language modelling as a multi-task
pr...
In this paper, we consider the syntactic properties of languages emerged...
In previous work, artificial agents were shown to achieve almost perfect...
Recent findings in multi-agent deep learning systems point towards the
e...
In this work, we present an alternative approach to making an agent
comp...
Referential games offer a grounded learning environment for neural agent...
We converted the recently developed BabyAI grid world platform to a
send...
Previous research into agent communication has shown that a pre-trained ...
Neural networks are surprisingly good at interpolating and perform remar...
Despite a multitude of empirical studies, little consensus exists on whe...
To cooperate with humans effectively, virtual agents need to be able to
...
Since their inception, encoder-decoder models have successfully been app...
This paper introduces the PhotoBook dataset, a large-scale collection of...
We present a detailed comparison of two types of sequence to sequence mo...
While sequence-to-sequence models have shown remarkable generalization p...
Learning to follow human instructions is a challenging task because whil...
We are interested in understanding how the ability to ground language in...
In this paper, we introduce Attentive Guidance (AG), a new mechanism to
...
Our goal is to explore how the abilities brought in by a dialogue manage...
Colorectal adenocarcinoma originating in intestinal glandular structures...