arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.07820cs.CLcs.LG
收藏

自然语言处理深度神经网络中多任务学习的经验评估

Empirical Evaluation of Multi-task Learning in Deep Neural Networks for Natural Language Processing

Beijing Ultrapower Software Co.,Ltd.(北京神州泰岳软件股份有限公司);University of Pennsylvania(宾夕法尼亚大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)

Jianquan Li, Xiaokang Liu, Wenpeng Yin, Min Yang, Liqun Ma, Yaohong Jin

摘要:

多任务学习(MTL)旨在通过利用多个相关任务中包含的有用信息来提高每个任务的整体性能。它在自然语言处理(NLP)中取得了巨大的成功。目前,许多MLT架构和学习机制已被提出用于各种NLP任务。然而,没有系统的探索和比较不同的MLT架构和学习机制,其强大的性能深入。在本文中,我们对典型的MTL方法进行了深入的研究,这些方法适用于广泛的代表性NLP任务。我们的主要目标是了解现有MTL方法在NLP任务中的优缺点,从而设计出新的混合架构,旨在结合它们的优势。

英文摘要:

Multi-Task Learning (MTL) aims at boosting the overall performance of each individual task by leveraging useful information contained in multiple related tasks. It has shown great success in natural language processing (NLP). Currently, a number of MLT architectures and learning mechanisms have been proposed for various NLP tasks. However, there is no systematic exploration and comparison of different MLT architectures and learning mechanisms for their strong performance in-depth. In this paper, we conduct a thorough examination of typical MTL methods on a broad range of representative NLP tasks. Our primary goal is to understand the merits and demerits of existing MTL methods in NLP tasks, thus devising new hybrid architectures intended to combine their strengths.

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。

↑