In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDIALOG curated in our work. The cur rent models indeed suffer from spurious correlations and have a tendency of generating irrelevant and generic responses. Inspired by causal discovery algorithms, we propose a novel model-agnostic method for training and inference of response generation model using a conditional independence classifier. The classifier is trained by a constrained self-training method, coined CONSTRAIN, to overcome data scarcity. The experimental results based on both human and automatic evaluation show that our method significantly outperforms the competitive baselines in terms of relevance, informativeness, and fluency.
翻译:在本文中,我们根据我们工作中整理的CGDIALOG文案,对开放域响应生成模型的虚假关联性进行了第一次研究。卷卷租金模型确实存在虚假关联性,并倾向于产生不相干和通用的响应。在因果发现算法的启发下,我们建议了一种新型的模型――不可知性方法,用于使用有条件的独立分类器培训和推断响应生成模型。分类师通过一种有限的自我培训方法,即CONTRAIN,来培训,以克服数据稀缺。基于人与自动评估的实验结果表明,我们的方法在相关性、信息性和流畅性方面大大超过了竞争性基线。</s>