arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.12733cs.CL
收藏

基于知识三元组的信息文本生成

Informative Text Generation from Knowledge Triples

University of Cambridge(剑桥大学);University of Pennsylvania(宾夕法尼亚大学);The Chinese University of Hong Kong(香港中文大学)

Zihao Fu, Yijiang River Dong, Lidong Bing, Wai Lam

摘要:

随着编码器-解码器体系结构的发展,研究人员能够研究更广泛类型数据的文本生成任务。其中,知识库到文本的目标是将一组知识三元组转换成人类可读的句子。在原始设置中,任务假设输入三元组和文本在具体知识/信息的角度上完全对齐。在本文中,我们扩展了这种设置,并探索如何促进训练模型生成更多信息的文本,即包含更多关于三元组实体的信息,但不是由输入三元组传达的。为了解决这个问题,我们提出了一种新的记忆增强生成器,采用记忆网络来记忆在训练过程中学到的有用知识,并利用这些信息与输入三元组一起在操作或测试阶段生成文本。我们从WebNLG中为我们的新设置获得了一个数据集,并进行了大量的实验来研究我们模型的有效性,并揭示了该设置的内在特征。

英文摘要:

As the development of the encoder-decoder architecture, researchers are able to study the text generation tasks with broader types of data. Among them, KB-to-text aims at converting a set of knowledge triples into human readable sentences. In the original setting, the task assumes that the input triples and the text are exactly aligned in the perspective of the embodied knowledge/information. In this paper, we extend this setting and explore how to facilitate the trained model to generate more informative text, namely, containing more information about the triple entities but not conveyed by the input triples. To solve this problem, we propose a novel memory augmented generator that employs a memory network to memorize the useful knowledge learned during the training and utilizes such information together with the input triples to generate text in the operational or testing phase. We derive a dataset from WebNLG for our new setting and conduct extensive experiments to investigate the effectiveness of our model as well as uncover the intrinsic characteristics of the setting.

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。

↑