For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on BART (Lewis et al., 2020), a pre-trained transformer encoder-decoder model, is trained to generate responses and recognize emotions simultaneously. Furthermore, we weight the losses for the tasks to control the update of parameters. Automatic evaluations and crowdsourced manual evaluations show that the proposed model makes generated responses more emotionally aware.
翻译:计算机要自然地与人类互动,就需要像人一样。 在本文中, 我们提出一个神经反应生成模型, 以多任务学习生成和分类, 重点是情感。 我们基于 BART ( Lewis等人, 2020年) 的模型, 是一个训练有素的变压器编码器- 解码器模型, 受过培训, 可以同时产生反应和识别情绪。 此外, 我们权衡损失, 以控制参数更新的任务 。 自动评估和众包手动评估显示, 拟议的模型能让反应在情感上得到更多了解 。