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 1805.08093cs.CL
收藏

NeuralREG:一种端到端的引用表达式生成方法

NeuralREG: An end-to-end approach to referring expression generation

Tilburg University(蒂尔堡大学);University of Leipzig(莱比锡大学);University of Paderborn(帕德博恩大学)

Thiago Castro Ferreira, Diego Moussallem, Ákos Kádár, Sander Wubben, Emiel Krahmer

摘要:

传统的指称表达生成(REG)模型首先决定文本中对话语实体的指称的形式,然后决定指称的内容,通常依赖于诸如显著性和语法功能之类的特征。在本文中,我们提出了一种新方法(NeuralREG),它依赖于深度神经网络,可以在没有显式特征提取的情况下一次性做出关于形式和内容的决定。使用WebNLG语料库的去词汇化版本,我们证明了神经模型在两个强基线上有了实质性的改进。数据和模型是公开的。

英文摘要:

Traditionally, Referring Expression Generation (REG) models first decide on the form and then on the content of references to discourse entities in text, typically relying on features such as salience and grammatical function. In this paper, we present a new approach (NeuralREG), relying on deep neural networks, which makes decisions about form and content in one go without explicit feature extraction. Using a delexicalized version of the WebNLG corpus, we show that the neural model substantially improves over two strong baselines. Data and models are publicly available.

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。

↑