Building Task-Oriented Visual Dialog Systems Through Alternative Optimization Between Dialog Policy and Language Generation [article]

Mingyang Zhou, Josh Arnold, Zhou Yu
2019 arXiv   pre-print
Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence (seq2seq) framework with the action space being the output vocabulary in the decoder. However, it is difficult to design a reward function that can achieve a balance between learning an effective policy and generating a natural dialog response. This paper proposes a novel framework that alternatively
more » ... ns a RL policy for image guessing and a supervised seq2seq model to improve dialog generation quality. We evaluate our framework on the GuessWhich task and the framework achieves the state-of-the-art performance in both task completion and dialog quality.
arXiv:1909.05365v2 fatcat:avidxwp3nfavjmlkrwizo6lxva