论文标题
一种生成的方法，用于标题和聚类Wikipedia部分
A Generative Approach to Titling and Clustering Wikipedia Sections
论文作者
论文摘要
我们通过一项新任务来评估有关信息组织的各种解码器的变压器编码器的性能：Wikipedia文章的截面标题。我们的分析表明，包含编码器输出的注意机制的解码器通过产生提取文本来实现高分的结果。相比之下，没有注意力的解码器更好地促进了语义编码，可用于生成截面的嵌入。我们还引入了一个新的损失功能，这进一步鼓励解码器生成高质量的嵌入。
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.
