Local or Global: The Variation in the Encoding of Style Across Sentiment and Formality

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PART X(2023)

引用 0|浏览0
暂无评分
摘要
Research on textual style transfer has observed that the concept of style can vary across domains. This research examines the encoding of style across the sentiment and formality domains and observes that formality appears to be more globally encoded, and sentiment more locally encoded. The work also shows how the encoding of a style can inform the appropriate choice of method to compute content preservation during textual style transfer.
更多
查看译文
关键词
Sentiment,Formality,Style,Local,Global
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要