论文标题
一项关于单词元插入学习的调查
A Survey on Word Meta-Embedding Learning
论文作者
论文摘要
Meta-ebbedding（ME）学习是一种新兴方法，它试图学习更准确的单词嵌入，并给定现有（源）单词嵌入作为唯一输入。 由于他们能够以紧凑的方式与卓越的性能合并多种源嵌入语义，因此我的学习在NLP的从业人员中广受欢迎。 据我们所知，没有关于我学习的系统调查，本文试图满足这一需求。 我们根据多种因素将学习方法分类，例如它们（a）是否在静态或上下文化的嵌入方式上操作，（b）以无监督的方式训练或（c）针对特定任务/域进行微调。 此外，我们讨论了现有ME学习方法的局限性，并突出了潜在的未来研究方向。
Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ability to incorporate semantics from multiple source embeddings in a compact manner with superior performance, ME learning has gained popularity among practitioners in NLP. To the best of our knowledge, there exist no prior systematic survey on ME learning and this paper attempts to fill this need. We classify ME learning methods according to multiple factors such as whether they (a) operate on static or contextualised embeddings, (b) trained in an unsupervised manner or (c) fine-tuned for a particular task/domain. Moreover, we discuss the limitations of existing ME learning methods and highlight potential future research directions.
