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 1804.09540cs.CLcs.AI
收藏

NE-Table:命名实体的神经键值表

NE-Table: A Neural key-value table for Named Entities

University of Michigan(密歇根大学);IBM Research(IBM研究院);Amazon Alexa-AI Research(亚马逊Alexa人工智能研究院)

Janarthanan Rajendran, Jatin Ganhotra, Xiaoxiao Guo, Mo Yu, Satinder Singh, Lazaros Polymenakos

摘要:

许多自然语言处理(NLP)任务依赖于使用包含在文本和外部知识源中的命名实体(NE)。虽然这对人类来说很容易,但目前依赖于学习的词嵌入的神经方法可能无法很好地执行这些NLP任务,特别是在存在词汇外(OOV)或罕见NE的情况下。在本文中,我们提出了一个解决这个问题的方法,并提出了实证评估:a)一个结构化的解释任务,b)三个相关的目标导向的对话任务,和c)阅读理解任务,这表明所提出的方法可以有效地处理在词汇和OOV NE。我们创建了dialog bAbI任务1、2和4的扩展版本以及CBT测试集的OOV版本,可在https://github.com/IBM/ne-table-datasets上获得。

英文摘要:

Many Natural Language Processing (NLP) tasks depend on using Named Entities (NEs) that are contained in texts and in external knowledge sources. While this is easy for humans, the present neural methods that rely on learned word embeddings may not perform well for these NLP tasks, especially in the presence of Out-Of-Vocabulary (OOV) or rare NEs. In this paper, we propose a solution for this problem, and present empirical evaluations on: a) a structured Question-Answering task, b) three related Goal-Oriented dialog tasks, and c) a Reading-Comprehension task, which show that the proposed method can be effective in dealing with both in-vocabulary and OOV NEs. We create extended versions of dialog bAbI tasks 1,2 and 4 and OOV versions of the CBT test set available at - https://github.com/IBM/ne-table-datasets.

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。

↑