arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.13401cs.CLcs.LG
收藏

将实体类型注入到语义引导的文本生成中

Injecting Entity Types into Entity-Guided Text Generation

University of Notre Dame(圣母大学);Microsoft Cognitive Services Research(微软认知服务研究院)

Xiangyu Dong, Wenhao Yu, Chenguang Zhu, Meng Jiang

摘要:

最近在深度生成建模方面的成功导致了自然语言生成(NLG)的重大进展。通过帮助推断摘要主题和生成连贯的内容,将实体转换为神经生成模型已经证明了很大的改进。为了增强实体在自然语言生成中的作用,本文提出在解码阶段对实体类型进行建模,以准确生成上下文词语。我们开发了一种新的NLG模型,根据给定的实体列表产生靶序列。我们的模型有一个多步骤的解码器,将实体类型注入到实体提及生成的过程中。在两个公共新闻数据集上的实验表明,类型注入的性能优于现有的类型嵌入串联基线。

英文摘要:

Recent successes in deep generative modeling have led to significant advances in natural language generation (NLG). Incorporating entities into neural generation models has demonstrated great improvements by assisting to infer the summary topic and to generate coherent content. To enhance the role of entity in NLG, in this paper, we aim to model the entity type in the decoding phase to generate contextual words accurately. We develop a novel NLG model to produce a target sequence based on a given list of entities. Our model has a multi-step decoder that injects the entity types into the process of entity mention generation. Experiments on two public news datasets demonstrate type injection performs better than existing type embedding concatenation baselines.

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。

↑