论文标题
通过各种顺序计划的数据到文本生成
Data-to-text Generation with Variational Sequential Planning
论文作者
论文摘要
我们考虑数据到文本生成的任务，该任务旨在从非语言输入中创建文本输出。我们专注于生成长形式文本，即具有多个段落的文档，并提出了一个神经模型，并通过负责以连贯且有意义的方式组织高级信息的计划组件增强了神经模型。我们通过结构化变分模型依次推断潜在计划，同时交织了计划和发电的步骤。文本是通过根据先前的变异决策和先前生成的文本来生成的。对两个数据之间的基准测试（Rotowire和MLB）进行的实验表明，我们的模型在有限的培训数据（例如几百个实例）面对有限的训练数据时效率优于强基础，并且是有效的样品。
We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, i.e., documents with multiple paragraphs, and propose a neural model enhanced with a planning component responsible for organizing high-level information in a coherent and meaningful way. We infer latent plans sequentially with a structured variational model, while interleaving the steps of planning and generation. Text is generated by conditioning on previous variational decisions and previously generated text. Experiments on two data-to-text benchmarks (RotoWire and MLB) show that our model outperforms strong baselines and is sample efficient in the face of limited training data (e.g., a few hundred instances).
