Generating Related Work
This addresses the challenge of efficiently summarizing related work for researchers, though it appears incremental as it builds on existing summarization techniques.
The paper tackled the problem of automatically generating related work sections for research papers by modeling the motivation behind citations, using a content planning model to create a tree of cited papers and a surface realization model for lexicalization. The model outperformed several strong state-of-the-art summarization models on a contributed ACL Anthology dataset.
Communicating new research ideas involves highlighting similarities and differences with past work. Authors write fluent, often long sections to survey the distinction of a new paper with related work. In this work we model generating related work sections while being cognisant of the motivation behind citing papers. Our content planning model generates a tree of cited papers before a surface realization model lexicalizes this skeleton. Our model outperforms several strong state-of-the-art summarization and multi-document summarization models on generating related work on an ACL Anthology (AA) based dataset which we contribute.