arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.05554cs.LGstat.ML
收藏

深度自动化多任务学习

Deep Automated Multi-task Learning

University of California, San Diego(加利福尼亚大学圣迭戈分校)

Davis Liang, Yan Shu

摘要:

多任务学习(MTL)最近有助于学习更好的表示服务于各种NLP任务。MTL旨在通过对次要任务的联合培训来提高主要任务的性能。本文介绍了自动化的任务,利用连续性的输入数据,作为次要任务的MTL模型。我们探索下一个单词预测,下一个字符预测,和遗漏的单词完成潜在的自动化任务。我们的研究结果表明,在一个主要任务上并行训练一个次要的自动化任务,可以提高主要任务的收敛速度和准确性。我们提出了两种方法来增强现有网络的自动化任务,并建立更好的性能,在主题预测,情感分析,和标签推荐。最后,我们证明了MTL模型可以在小而口语化的数据集上表现良好。

英文摘要:

Multi-task learning (MTL) has recently contributed to learning better representations in service of various NLP tasks. MTL aims at improving the performance of a primary task, by jointly training on a secondary task. This paper introduces automated tasks, which exploit the sequential nature of the input data, as secondary tasks in an MTL model. We explore next word prediction, next character prediction, and missing word completion as potential automated tasks. Our results show that training on a primary task in parallel with a secondary automated task improves both the convergence speed and accuracy for the primary task. We suggest two methods for augmenting an existing network with automated tasks and establish better performance in topic prediction, sentiment analysis, and hashtag recommendation. Finally, we show that the MTL models can perform well on datasets that are small and colloquial by nature.

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。

↑