Advanced search
Start date
Betweenand


What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialogue

Author(s):
Shuklar, Pushkar ; Elmadjian, Carlos ; Sharan, Richika ; Kulkarni, Vivek ; Wang, William Yang ; Turk, Matthew ; ACL ; Korhonen, A ; Traum, D ; Marquez, L
Total Authors: 10
Document type: Journal article
Source: 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019); v. N/A, p. 10-pg., 2019-01-01.
Abstract

The ability to engage in goal-oriented conversations has allowed humans to gain knowledge, reduce uncertainty, and perform tasks more efficiently. Artificial agents, however, are still far behind humans in having goal-driven conversations. In this work, we focus on the task of goal-oriented visual dialogue, aiming to automatically generate a series of questions about an image with a single objective. This task is challenging, since these questions must not only be consistent with a strategy to achieve a goal, but also consider the contextual information in the image. We propose an end-to-end goal-oriented visual dialogue system, that combines reinforcement learning with regularized information gain. Unlike previous approaches that have been proposed for the task, our work is motivated by the Rational Speech Act framework, which models the process of human inquiry to reach a goal. We test the two versions of our model on the GuessWhat?! dataset, obtaining significant results that outperform the current state-of-the-art models in the task of generating questions to find an undisclosed object in an image. (AU)

FAPESP's process: 15/26802-1 - Augmented cognition using wearable computing
Grantee:Carlos Eduardo Leão Elmadjian
Support Opportunities: Scholarships in Brazil - Doctorate (Direct)