A Generative Approach to Titling and Clustering Wikipedia Sections

05/22/2020
by   Anjalie Field, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset