Towards Annotating and Creating Sub-Sentence Summary Highlights
This work addresses the need for more concise and fluent summaries in text processing, though it appears incremental by building on existing highlighting methods.
The paper tackles the problem of generating summary highlights at the sub-sentence level by annotating summary-worthy sub-sentences and training classifiers, resulting in a formulation that reduces task complexity for sentence compression.
Highlighting is a powerful tool to pick out important content and emphasize. Creating summary highlights at the sub-sentence level is particularly desirable, because sub-sentences are more concise than whole sentences. They are also better suited than individual words and phrases that can potentially lead to disfluent, fragmented summaries. In this paper we seek to generate summary highlights by annotating summary-worthy sub-sentences and teaching classifiers to do the same. We frame the task as jointly selecting important sentences and identifying a single most informative textual unit from each sentence. This formulation dramatically reduces the task complexity involved in sentence compression. Our study provides new benchmarks and baselines for generating highlights at the sub-sentence level.