The ability to detect Out-of-Domain (OOD) inputs has been a critical requirement in many real-world NLP applications since the inclusion of unsupported OOD inputs may lead to catastrophic failure of systems. However, it remains an empirical question whether current algorithms can tackle such problem reliably in a realistic scenario where zero OOD training data is available. In this study, we propose ProtoInfoMax, a new architecture that extends Prototypical Networks to simultaneously process In-Domain (ID) and OOD sentences via Mutual Information Maximization (InfoMax) objective. Experimental results show that our proposed method can substantially improve performance up to 20% for OOD detection in low resource settings of text classification. We also show that ProtoInfoMax is less prone to typical over-confidence Error of Neural Networks, leading to more reliable ID and OOD prediction outcomes.

翻译：检测外部输入的能力是许多实际NLP应用的关键要求,因为纳入未经支持的OOD输入可能导致系统的灾难性故障,然而,目前算法能否在现实的情景下可靠地解决这一问题,而OOD培训数据是零的,这仍然是一个实证问题。在本研究中,我们提出了ProtoInfoMax,这是一个新的结构,通过相互信息最大化(InfoMax)目标,将原型网络扩展至同时处理在Doma(ID)和OOOD判决。实验结果表明,我们提出的方法可以大大改善在文本分类低资源环境下OOD检测的性能,达到20%。我们还表明,ProtoInfoMax较不易发生典型的神经网络过度信任错误,导致更可靠的ID和OOD预测结果。