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 2012.08958cs.CL
收藏

为您的企业采用NLP时需要考虑的成本

Costs to Consider in Adopting NLP for Your Business

Kata.ai Research Team(Kata.ai研究团队);Universitas Indonesia(印度尼西亚大学)

Made Nindyatama Nityasya, Haryo Akbarianto Wibowo, Radityo Eko Prasojo, Alham Fikri Aji

摘要:

自然语言处理(NLP)的最新进展在很大程度上推动了基于深度转换器的模型成为最先进的技术,而无需过多考虑生产和使用成本。计划在业务中采用这些方法的公司面临困难,因为缺乏机器,数据和人力资源来构建它们。我们比较的性能和成本的经典学习算法的最新的共同序列和文本标记任务。在我们的工业数据集中,我们发现经典模型的性能通常与深度神经模型相当,尽管成本较低。我们展示了各个模型中性能增益和成本之间的权衡,以提供更多关于AI枢转业务的见解。此外,我们呼吁对低成本模型进行更多研究,特别是针对资源不足的语言。

英文摘要:

Recent advances in Natural Language Processing (NLP) have largely pushed deep transformer-based models as the go-to state-of-the-art technique without much regard to the production and utilization cost. Companies planning to adopt these methods into their business face difficulties because of the lack of machine, data, and human resources to build them. We compare both the performance and the cost of classical learning algorithms to the latest ones in common sequence and text labeling tasks. In our industrial datasets, we find that classical models often perform on par with deep neural ones despite the lower cost. We show the trade-off between performance gain and the cost across the models to give more insights for AI-pivoting business. Further, we call for more research into low-cost models, especially for under-resourced languages.

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。

↑