11 papers with code • 4 benchmarks • 7 datasets
Image credit: TLDR: Extreme Summarization of Scientific Documents
LibrariesUse these libraries to find Extreme Summarization models and implementations
Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension.
Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization
We introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling approach.
We introduce 'extreme summarization', a new single-document summarization task which aims at creating a short, one-sentence news summary answering the question ``What is the article about?''.
Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles
Multi-document summarization is a challenging task for which there exists little large-scale datasets.
We present IndicBART, a multilingual, sequence-to-sequence pre-trained model focusing on 11 Indic languages and English.
Recent models in developing summarization systems consist of millions of parameters and the model performance is highly dependent on the abundance of training data.
CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision
Scientific extreme summarization (TLDR) aims to form ultra-short summaries of scientific papers.
The number of scientific publications nowadays is rapidly increasing, causing information overload for researchers and making it hard for scholars to keep up to date with current trends and lines of work.