Existing KBQA approaches, despite achieving strong performance on i.i.d. test data, often struggle in generalizing to questions involving unseen KB schema items. Prior ranking-based approaches have shown some success in generalization, but suffer from the coverage issue. We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability. Our approach first uses a contrastive ranker to rank a set of candidate logical forms obtained by searching over the knowledge graph. It then introduces a tailored generation model conditioned on the question and the top-ranked candidates to compose the final logical form. We achieve new state-of-the-art results on GrailQA and WebQSP datasets. In particular, our method surpasses the prior state-of-the-art by a large margin on the GrailQA leaderboard. In addition, RnG-KBQA outperforms all prior approaches on the popular WebQSP benchmark, even including the ones that use the oracle entity linking. The experimental results demonstrate the effectiveness of the interplay between ranking and generation, which leads to the superior performance of our proposed approach across all settings with especially strong improvements in zero-shot generalization.

中文翻译：

---

RnG-KBQA：知识库问答的生成增强迭代排名

现有的 KBQA 方法，尽管在 iid 测试数据上取得了强大的性能，但在推广涉及未见过的 KB 模式项目的问题时经常遇到困难。先前基于排名的方法在泛化方面取得了一些成功，但存在覆盖问题。我们提出了 RnG-KBQA，一种用于 KBQA 的排序和生成方法，它通过生成模型解决了覆盖问题，同时保留了强大的泛化能力。我们的方法首先使用对比排序器对通过搜索知识图获得的一组候选逻辑形式进行排序。然后，它引入了一个以问题和排名靠前的候选者为条件的定制生成模型，以组成最终的逻辑形式。我们在 GrailQA 和 WebQSP 数据集上取得了最新的最新成果。特别是，我们的方法在 GrailQA 排行榜上大大超过了先前的最先进技术。此外，RnG-KBQA 在流行的 WebQSP 基准测试中优于所有先前的方法，甚至包括使用 oracle 实体链接的方法。实验结果证明了排序和生成之间相互作用的有效性，这导致我们提出的方法在所有设置中的卓越性能，尤其是在零样本泛化方面的改进。