arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.01082cs.CLcs.AI
收藏

多模态开放域对话

Multi-Modal Open-Domain Dialogue

Kurt Shuster, Eric Michael Smith, Da Ju, Jason Weston

摘要:

最近在开放域会话代理中的工作已经证明,可以通过预训练数据和模型大小的大规模缩放来实现模型灵活性和人性度量的显著改进(Adiwardana等人,2020; Roller等人,2020年)。然而,如果我们想构建具有类似人类能力的智能体,我们必须扩展到不仅仅处理文本。一个特别重要的主题是能够看到图像和交流所感知的内容。为了让人类参与多模态对话,我们研究了将最先进的开放域对话代理组件与最先进的视觉模型组件相结合。我们研究结合不同的图像融合方案和域自适应预训练和微调策略,并表明我们最好的结果模型在多模态对话中优于强大的现有模型,同时表现得与其前身(纯文本)BlenderBot一样好(Roller等人,2020年,在基于文本的对话中。我们还调查,并在我们的最终模型中纳入安全组件,并表明,这种努力不会降低模型的性能方面的可靠性指标。

英文摘要:

Recent work in open-domain conversational agents has demonstrated that significant improvements in model engagingness and humanness metrics can be achieved via massive scaling in both pre-training data and model size (Adiwardana et al., 2020; Roller et al., 2020). However, if we want to build agents with human-like abilities, we must expand beyond handling just text. A particularly important topic is the ability to see images and communicate about what is perceived. With the goal of engaging humans in multi-modal dialogue, we investigate combining components from state-of-the-art open-domain dialogue agents with those from state-of-the-art vision models. We study incorporating different image fusion schemes and domain-adaptive pre-training and fine-tuning strategies, and show that our best resulting model outperforms strong existing models in multi-modal dialogue while simultaneously performing as well as its predecessor (text-only) BlenderBot (Roller et al., 2020) in text-based conversation. We additionally investigate and incorporate safety components in our final model, and show that such efforts do not diminish model performance with respect to engagingness metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑