arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1909.09986cs.CL
收藏

提高基于规划的神经网络数据文本生成的质量和效率

Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generation

Bar Ilan University(巴伊兰大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所)

Amit Moryossef, Ido Dagan, Yoav Goldberg

摘要:

我们遵循我们在Moryossef et al(2019)中提出的神经数据到文本生成的分步方法,其中生成过程分为文本规划阶段和规划实现阶段。我们对该框架提出了四个扩展:(1)我们引入了一个可训练的神经规划组件,它可以比原始规划器快几个数量级地生成有效的计划;(2)我们引入了输入提示,提高了模型处理不可见关系和实体的能力;(3)我们引入了一个通过重新排序进行验证的阶段,大大提高了结果文本的忠实性;(4)引入了一个简单有效的指称表达式生成模块。这些扩展导致生成过程更快、更流畅和更准确。

英文摘要:

We follow the step-by-step approach to neural data-to-text generation we proposed in Moryossef et al (2019), in which the generation process is divided into a text-planning stage followed by a plan-realization stage. We suggest four extensions to that framework: (1) we introduce a trainable neural planning component that can generate effective plans several orders of magnitude faster than the original planner; (2) we incorporate typing hints that improve the model's ability to deal with unseen relations and entities; (3) we introduce a verification-by-reranking stage that substantially improves the faithfulness of the resulting texts; (4) we incorporate a simple but effective referring expression generation module. These extensions result in a generation process that is faster, more fluent, and more accurate.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑