Name
Title | ||
|---|---|---|
Zero-Shot Aspect-Based Scientific Document Summarization using Self-Supervised Pre-training |
Abstract | ||
|---|---|---|
We study the zero-shot setting for the aspect-based scientific document summarization task. Summarizing scientific documents with respect to an aspect can remarkably improve document assistance systems and readers experience. However, existing large-scale datasets contain a limited variety of aspects, causing summarization models to over-fit to a small set of aspects and a specific domain. We establish baseline results in zero-shot performance (over unseen aspects and the presence of domain shift), paraphrasing, leave-one-out, and limited supervised samples experimental setups. We propose a self-supervised pre-training approach to enhance the zero-shot performance. We leverage the PubMed structured abstracts to create a biomedical aspect-based summarization dataset. Experimental results on the PubMed and FacetSum aspect-based datasets show promising performance when the model is pre trained using unlabelled in-domain data.(1) |
Year | DOI | Venue |
|---|---|---|
2022 | 10.18653/v1/2022.bionlp-1.5 | PROCEEDINGS OF THE 21ST WORKSHOP ON BIOMEDICAL LANGUAGE PROCESSING (BIONLP 2022) |
DocType | Volume | Citations |
Conference | Proceedings of the 21st Workshop on Biomedical Language Processing | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Amir Soleimani | 1 | 0 | 0.34 |
| Vassilina Nikoulina | 2 | 0 | 0.34 |
| Benoit Favre | 3 | 0 | 0.34 |
| Salah Ait Mokhtar | 4 | 0 | 0.34 |