GUIR @ LongSumm 2020: Learning to Generate Long Summaries from Scientific Documents
By Sajad Sotudeh Gharebagh, Arman Cohan, Nazli Goharian. 2020
11 citations recorded by the source corpus.
This paper presents our methods for the LongSumm 2020: Shared Task on Generating Long Summaries for Scientific Documents, where the task is to generatelong summaries given a set of scientific papers provided by the organizers. We explore 3 main approaches for this task: 1. An extractive approach using a BERT-based summarization model; 2. A two stage model that additionally includes an abstraction step using BART; and 3. A new multi-tasking approach on incorporating document structure into the summarizer. We found that our new multi-tasking approach outperforms the two other methods by large margins. Among 9 participants in the shared task, our best model ranks top according to Rouge-1 score (53.11%) while staying competitive in terms of Rouge-2.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jan Leike
- Jeff Wu
- Nazli Goharian
- Arman Cohan
- Ryan J. Lowe
- Daniel M. Ziegler
- Paul Christiano
- Sajad Sotudeh
In Natural Language Processing
- Nazli Goharian
- Arman Cohan
- Sajad Sotudeh
- Paul Christiano
- Daniel M. Ziegler
- Ryan J. Lowe
- Nissan Stiennon
- Jan Leike
Citations in the corpus
- Recursively Summarizing Books with Human Feedback (2021, methodology): “…2019; Cohan et al., 2018; Xiao and Carenini, 2019; Zhao et al., 2020; Sotudeh et al., 2020), and patents (Sharma et al., 2019), as well as multi-document summarization (Liu et al., 2018; Ma et al., 2020; Gharebagh et al., 2020; Chandrasekaran et al., 2020; Liu and Lapata, 2019a; Gao et al., 2020).”
- Overview and Insights from the Shared Tasks at Scholarly Document Processing 2020: CL-SciSumm, LaySumm and LongSumm (2020, unknown): “In addition, we randomly selected 5 summaries from the top-3 ranked systems, namely: GUIR , Summaformers and IIITBH-IITP , to be evaluated by experts.”
- On Generating Extended Summaries of Long Documents (2020, methodology): “To those who seek more detailed information about a document without having to cover the entire document, an extended or long summary can be desirable (Chandrasekaran et al. 2020; Sotudeh, Cohan, and Goharian 2020; Ghosh Roy et al. 2020).”