Retrieval augmentation, which enhances downstream models by a knowledge retriever and an external corpus instead of by merely increasing the number of model parameters, has been successfully applied to many natural language processing (NLP) tasks such as text classification, question answering and so on. However, existing methods that separately or asynchronously train the retriever and downstream model mainly due to the non-differentiability between the two parts, usually lead to degraded performance compared to end-to-end joint training. In this paper, we propose Differentiable Retrieval Augmentation via Generative lANguage modeling(Dragan), to address this problem by a novel differentiable reformulation. We demonstrate the effectiveness of our proposed method on a challenging NLP task in e-commerce search, namely query intent classification. Both the experimental results and ablation study show that the proposed method significantly and reasonably improves the state-of-the-art baselines on both offline evaluation and online A/B test.

翻译：检索增强通过知识检索器和外部语料库增强下游模型，而非仅增加模型参数数量，已成功应用于文本分类、问答等多项自然语言处理任务。然而，现有方法通常因检索器与下游模型之间的不可微性而采用分离或异步训练，导致性能较端到端联合训练有所下降。本文提出基于生成式语言建模的可微检索增强方法（Dragan），通过创新的可微重构解决该问题。我们以电商搜索中的查询意图分类这一具有挑战性的自然语言处理任务为场景，验证了所提方法的有效性。实验结果与消融研究均表明，该方法在离线评估和在线A/B测试中显著且合理地提升了当前最优基线性能。