Attention based Sentence Extraction from Scientific Articles using Pseudo-Labeled data
This addresses the challenge of efficiently summarizing scientific papers for researchers and readers, though it appears to be an incremental improvement over existing extractive methods.
The paper tackles the problem of automatically extracting important sentences from scientific articles for abstract generation, proposing a weakly supervised attention-based deep learning architecture that achieves better performance than state-of-the-art extractive techniques on several ROUGE metrics.
In this work, we present a weakly supervised sentence extraction technique for identifying important sentences in scientific papers that are worthy of inclusion in the abstract. We propose a new attention based deep learning architecture that jointly learns to identify important content, as well as the cue phrases that are indicative of summary worthy sentences. We propose a new context embedding technique for determining the focus of a given paper using topic models and use it jointly with an LSTM based sequence encoder to learn attention weights across the sentence words. We use a collection of articles publicly available through ACL anthology for our experiments. Our system achieves a performance that is better, in terms of several ROUGE metrics, as compared to several state of art extractive techniques. It also generates more coherent summaries and preserves the overall structure of the document.