Article-Journal

Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering

Going for GOAL: A Resource for Grounded Football Commentaries

Exploring Multi-Modal Representations for Ambiguity Detection & Coreference Resolution in the SIMMC 2.0 Challenge

Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion

An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games

Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games

CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning

Bridging the gap between linked open data-based recommender systems and distributed representations

Deep Learning and Hierarchical Reinforcement Learning for modeling a Conversational Recommender System

Iterative Multi-document Neural Attention for Multiple Answer Prediction