A Joint Speaker-Listener-Reinforcer Model for Referring Expressions
A Joint Speaker-Listener-Reinforcer Model for Referring Expressions
复制标题
DOI：
10.1109/cvpr.2017.375
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
Licheng Yu;Hao Tan;Mohit Bansal;Tamara L. Berg
中科院分区：
文献类型：
--
作者：
Licheng Yu;Hao Tan;Mohit Bansal;Tamara L. Berg
指称表达是用于识别场景中特定对象的自然语言结构。在本文中，我们提出了一个统一的框架，指的表达理解和生成的任务。我们的模型由三个模块组成：扬声器，听众和发音器。说话者生成指称表达，听话者生成指称表达，而话语者引入奖励函数来引导对更具区分性的表达的采样。发音者-说话者模块在端到端学习框架中进行联合训练，允许模块在学习过程中相互了解，同时也受益于辨别性发音者的反馈。我们证明了这个统一的框架和训练在三个参考表达数据集上实现了最先进的理解和生成结果。
Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a unified framework for the tasks of referring expression comprehension and generation. Our model is composed of three modules: speaker, listener, and reinforcer. The speaker generates referring expressions, the listener comprehends referring expressions, and the reinforcer introduces a reward function to guide sampling of more discriminative expressions. The listener-speaker modules are trained jointly in an end-to-end learning framework, allowing the modules to be aware of one another during learning while also benefiting from the discriminative reinforcer’s feedback. We demonstrate that this unified framework and training achieves state-of-the-art results for both comprehension and generation on three referring expression datasets.