arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06057cs.CL
收藏

个性化词嵌入的价值探索

Exploring the Value of Personalized Word Embeddings

University of Michigan(密歇根大学)

Charles Welch, Jonathan K. Kummerfeld, Verónica Pérez-Rosas, Rada Mihalcea

摘要:

在本文中,我们介绍了个性化的词嵌入,并检查他们的语言建模的价值。我们比较了我们提出的预测模型的性能时,使用个性化与通用的单词表示,并研究如何利用这些表示来提高性能。我们提供了在构建个性化模型时可以更准确地预测哪些类型的单词的见解。我们的研究结果表明,属于特定的心理语言学类别的一个子集的话往往会在他们的代表不同的用户和通用和个性化的词嵌入相结合,产生最好的性能,4.7%的相对减少困惑。此外,我们表明,使用个性化的词嵌入的语言模型可以有效地用于作者归属。

英文摘要:

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how these representations can be leveraged for improved performance. We provide insight into what types of words can be more accurately predicted when building personalized models. Our results show that a subset of words belonging to specific psycholinguistic categories tend to vary more in their representations across users and that combining generic and personalized word embeddings yields the best performance, with a 4.7% relative reduction in perplexity. Additionally, we show that a language model using personalized word embeddings can be effectively used for authorship attribution.

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。

↑