Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of selection among many fine-grained labels. Inspired by dense retrieval methods for passage finding in open-domain QA, we propose a reformulation of large-space discriminative NLU tasks as a learning-to-retrieve task, leading to a novel solution named Dense Decision Retrieval (DDR ). Instead of predicting fine-grained decisions as logits, DDR adopts a dual-encoder architecture that learns to predict by retrieving from a decision thesaurus. This approach not only leverages rich indirect supervision signals from easy-to-consume learning resources for dense retrieval, it also leads to enhanced prediction generalizability with a semantically meaningful representation of the large decision space. When evaluated on tasks with decision spaces ranging from hundreds to hundred-thousand scales, DDR outperforms strong baselines greatly by 27.54% in P@1 on two extreme multi-label classification tasks, 1.17% in F1 score ultra-fine entity typing, and 1.26% in accuracy on three few-shot intent classification tasks on average. Code and resources are available at https://github.com/luka-group/DDR

翻译：许多判别式自然语言理解（NLU）任务具有巨大的标签空间。由于每个标签的训练实例匮乏，且需要在众多细粒度标签中进行区分，学习这种大规模决策的过程尤为困难。受开放域问答中段落检索的稠密检索方法启发，我们将大规模判别式NLU任务重新定义为检索任务，提出创新性解决方案——稠密决策检索（Dense Decision Retrieval, DDR）。DDR并未将细粒度决策预测为逻辑回归值，而是采用双编码器架构，通过从决策同义词库中检索来学习预测。该方法不仅能从易于获取的学习资源中获取丰富的间接监督信号以支持稠密检索，还能通过具有语义意义的大规模决策空间表示增强预测泛化能力。在决策空间从数百到十万规模的多个任务中评估时，DDR在两个极端多标签分类任务上P@1指标提升27.54%，在超细粒度实体类型识别任务上F1分数提升1.17%，在三个少样本意图分类任务上平均准确率提升1.26%。代码与资源已开源至https://github.com/luka-group/DDR