| Challenge: | TLDR generation requires expert background knowledge and understanding of complex domain-specific language. |
| Approach: | They propose a learning strategy that exploits titles as an auxiliary training signal. |
| Outcome: | The proposed method improves upon strong baselines under both automated metrics and human evaluations. |
Similar Papers
CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision (2022.emnlp-main)
Copied to clipboard
| Challenge: | Scientific extreme summarization (TLDR) aims to form ultra-short summaries of scientific papers . previous attempts failed to scale up due to heavy human annotation and domain expertise . |
| Approach: | They propose a method to automatically extract TLDR summaries from scientific papers . they propose 'citeSum' with no human annotation, which is 30 times larger than SciTLDR . |
| Outcome: | The proposed approach outperforms most fully-supervised methods on SciTLDR without fine-tuning and achieves state-of-the-art results with only 128 examples. |
TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks (P19-1)
Copied to clipboard
| Challenge: | Currently, no large-scale training data is available for the task of scientific paper summarization. |
| Approach: | They propose a method that automatically generates scientific paper summaries by utilizing videos of scientific conferences. |
| Outcome: | The proposed model performs similar to models trained on a dataset of summaries created manually. |
Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles (2020.emnlp-main)
Copied to clipboard
| Challenge: | Multi-XScience is a dataset construction protocol that favours abstractive modeling approaches. |
| Approach: | They propose a large-scale multi-document summarization dataset that is based on articles and lexical databases and WordNet synonymy information to generate related-work sections of a paper. |
| Outcome: | The proposed method is based on lexical databases and WordNet synonymy information to write related work sections of a paper based upon their abstract and the articles they reference. |
Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to summarize documents are not extractive and require an abstractive approach. |
| Approach: | They propose a novel abstractive model which is conditioned on the article’s topics and based entirely on convolutional neural networks. |
| Outcome: | The proposed model outperforms an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans. |
TSTR: Too Short to Represent, Summarize with Details! Intro-Guided Extended Summary Generation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for extractive and abstract summarization are limited to short abstracts . however, extended summaries provide detailed information beyond coarse information . |
| Approach: | They propose an extractive summarization tool that utilizes the introductory information of documents as pointers to their salient information. |
| Outcome: | The proposed extractive summarization improves on existing datasets with human-written summaries . the proposed summarizing improves in terms of cohesion and completeness compared to baselines and state-of-the-art . |
A Summarization System for Scientific Documents (D19-3)
Copied to clipboard
Shai Erera, Michal Shmueli-Scheuer, Guy Feigenblat, Ora Peled Nakash, Odellia Boni, Haggai Roitman, Doron Cohen, Bar Weiner, Yosi Mass, Or Rivlin, Guy Lev, Achiya Jerbi, Jonathan Herzig, Yufang Hou, Charles Jochim, Martin Gleize, Francesca Bonin, Francesca Bonin, David Konopnicki
| Challenge: | a qualitative user study identified the most valuable scenarios for scientific content consumption. |
| Approach: | They propose a system that retrieves and summarizes scientific documents for a given information need. |
| Outcome: | The proposed system ingested 270,000 scientific papers and validated with human experts. |
BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization (P19-1)
Copied to clipboard
| Challenge: | Existing text summarization datasets are compiled from news articles, where summary-worthy content often appears in the beginning of input articles. |
| Approach: | They present a novel dataset, BIGPATENT, consisting of 1.3 million records of U.S. patent documents along with human written abstractive summaries. |
| Outcome: | The proposed dataset is compared with existing summarization datasets and demonstrates that salient content is evenly distributed in the input. |
ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing statistical phrasal or hierarchical machine translation systems relies on a large set of translation rules which results in engineering challenges. |
| Approach: | They propose to use factorized grammar from the field of linguistics as more general translation rules from XTAG English Grammar to generate a manually crafted summarization dataset. |
| Outcome: | The proposed method outperforms existing methods on low-resource language translation tasks with less training data. |
Two Huge Title and Keyword Generation Corpora of Research Articles (2020.lrec-1)
Copied to clipboard
| Challenge: | Recent advances in sequence-to-sequence learning with neural networks have improved the quality of automatically generated text summaries and document keywords. |
| Approach: | They propose to use OAGSX and OAGKX datasets to analyze text summaries and document keywords. |
| Outcome: | The proposed models perform better than previous models on two large datasets . the authors hope to use the results to derive subsets of research articles from more disciplines . |
ROUGE-SciQFS: A ROUGE-based Method to Automatically Create Datasets for Scientific Query-Focused Summarization (2025.coling-main)
Copied to clipboard
| Challenge: | Scientific Query-Focused Summarization (Sci-QFS) has lagged in development due to the lack of data. |
| Approach: | They propose a method to take advantage of existing academic papers to obtain large-scale datasets for this task automatically. |
| Outcome: | The proposed method outperforms existing models on the datasets and shows that it is relatively straightforward for humans. |