Better Highlighting: Creating Sub-Sentence Summary Highlights
This work addresses the need for better document summarization tools for readers dealing with large volumes of text, though it appears incremental as it builds on existing highlighting and summarization techniques.
The paper tackles the problem of generating sub-sentence summary highlights to help readers navigate large texts, presenting a method that combines determinantal point processes and deep contextualized representations to produce self-contained, non-redundant highlights, with extensive experiments on summarization datasets showing promising results.
Amongst the best means to summarize is highlighting. In this paper, we aim to generate summary highlights to be overlaid on the original documents to make it easier for readers to sift through a large amount of text. The method allows summaries to be understood in context to prevent a summarizer from distorting the original meaning, of which abstractive summarizers usually fall short. In particular, we present a new method to produce self-contained highlights that are understandable on their own to avoid confusion. Our method combines determinantal point processes and deep contextualized representations to identify an optimal set of sub-sentence segments that are both important and non-redundant to form summary highlights. To demonstrate the flexibility and modeling power of our method, we conduct extensive experiments on summarization datasets. Our analysis provides evidence that highlighting is a promising avenue of research towards future summarization.