Multimodal Representations for Teacher-Guided Compositional Visual Reasoning

no code implementations • 24 Oct 2023 • Wafa Aissa, Marin Ferecatu, Michel Crucianu

Neural Module Networks (NMN) are a compelling method for visual question answering, enabling the translation of a question into a program consisting of a series of reasoning sub-tasks that are sequentially executed on the image to produce an answer.

Question Answering Visual Question Answering +1

Curriculum Learning for Compositional Visual Reasoning

no code implementations • 27 Mar 2023 • Wafa Aissa, Marin Ferecatu, Michel Crucianu

Visual Question Answering (VQA) is a complex task requiring large datasets and expensive training.

Question Answering Visual Question Answering +1

A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems

no code implementations • WS 2018 • Wafa Aissa, Laure Soulier, Ludovic Denoyer

Search-oriented conversational systems rely on information needs expressed in natural language (NL).

reinforcement-learning Reinforcement Learning (RL) +1