A Generative Approach to Titling and Clustering Wikipedia Sections

NEURAL GENERATION AND TRANSLATION(2020)

引用 3|浏览26
暂无评分
摘要
We evaluate the performance of transformer encoders with various decoders for information organization through a new task: generation of section headings for Wikipedia articles. Our analysis shows that decoders containing attention mechanisms over the encoder output achieve high-scoring results by generating extractive text. In contrast, a decoder without attention better facilitates semantic encoding and can be used to generate section embeddings. We additionally introduce a new loss function, which further encourages the decoder to generate high-quality embeddings.
更多
查看译文
关键词
titling,sections,generative approach
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