论文标题
自然语言生成的联合发电机级学习
Joint Generator-Ranker Learning for Natural Language Generation
论文作者
论文摘要
生成 - 然后是一种广泛使用文本生成的机制，生成器会产生多个文本候选者，而排名者在文本候选者中选择了最好的文本。但是，现有方法通常会单独训练发电机和排名者，从而忽略了可以进一步提高发电质量的相互反馈。为了应对这一限制，我们提出了JGR，这是一种新型的联合培训算法，将发电机和排名整合到一个框架中。 JGR通过混合目标优化了生成器，该过程结合了数据的可能性和排名奖励，并通过比较发电机输出的对比损失来训练排名。通过迭代更新发电机和排名，JGR可以有效地协调他们的学习并共同提高其质量。我们在各种文本生成任务上评估JGR，并证明它超过了三个公共一代方案的四个公共数据集上的现有方法。我们的代码和模型可在https://github.com/microsoft/prophetnet/tree/master/jgr上公开获取。
Generate-then-rank is a widely used mechanism for text generation, where a generator produces multiple text candidates and a ranker chooses the best one among the text candidates. However, existing methods usually train the generator and the ranker individually, neglecting the mutual feedback that could further enhance the generation quality. To tackle this limitation, we propose JGR, a novel joint training algorithm that integrates the generator and the ranker in a single framework. JGR optimizes the generator with a hybrid objective that combines data likelihood and ranker reward, and trains the ranker with a contrastive loss that compares the generator outputs. By iteratively updating the generator and the ranker, JGR can effectively harmonize their learning and enhance their quality jointly. We evaluate JGR on various text generation tasks and demonstrate that it surpasses existing methods on four public datasets across three common generation scenarios. Our code and models are publicly available at https://github.com/microsoft/ProphetNet/tree/master/JGR.
