论文标题
自然语言处理的有效方法：调查
Efficient Methods for Natural Language Processing: A Survey
论文作者
论文摘要
自然语言处理（NLP）的最新工作从缩放模型参数和培训数据产生了吸引人的结果；但是，仅使用比例来提高绩效意味着资源消耗也会增长。这些资源包括数据，时间，存储或能源，所有这些资源自然受到限制且分布不均。这激发了对有效方法的研究，这些方法需要更少的资源才能获得类似的结果。该调查综合并关联了有效NLP中的当前方法和发现。我们旨在为在有限的资源下进行NLP提供指南，并指向有前途的研究方向，以开发更有效的方法。
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows. Such resources include data, time, storage, or energy, all of which are naturally limited and unevenly distributed. This motivates research into efficient methods that require fewer resources to achieve similar results. This survey synthesizes and relates current methods and findings in efficient NLP. We aim to provide both guidance for conducting NLP under limited resources, and point towards promising research directions for developing more efficient methods.
