Extractive Research Slide Generation Using Windowed Labeling Ranking
This work addresses the labor-intensive task of slide generation for researchers and practitioners, but it is incremental as it builds on existing extractive summarization techniques.
The authors tackled the problem of automatically generating presentation slides for scientific papers by proposing a windowed labeling ranking method, which outperformed baseline methods including SummaRuNNer with a significant margin in ROUGE scores.
Presentation slides describing the content of scientific and technical papers are an efficient and effective way to present that work. However, manually generating presentation slides is labor intensive. We propose a method to automatically generate slides for scientific papers based on a corpus of 5000 paper-slide pairs compiled from conference proceedings websites. The sentence labeling module of our method is based on SummaRuNNer, a neural sequence model for extractive summarization. Instead of ranking sentences based on semantic similarities in the whole document, our algorithm measures importance and novelty of sentences by combining semantic and lexical features within a sentence window. Our method outperforms several baseline methods including SummaRuNNer by a significant margin in terms of ROUGE score.