← Back to papers
2020 EMNLP EMNLP 2020

GUIR @ LongSumm 2020: Learning to Generate Long Summaries from Scientific Documents

Abstract

AbstractThis 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.

🌉 Interdisciplinary Bridge — Deep Learning and Interdisciplinary and Machine Learning and Natural Language Processing
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Sajad Sotudeh Gharebagh , Arman Cohan , Nazli Goharian

Topics

Machine Learning > Core Methods > Representation Learning Natural Language Processing > Generation > Summarization Natural Language Processing > Generation > Text Generation Interdisciplinary > Linguistics > Computational Linguistics Machine Learning > Learning Types > Multi-Task Learning Natural Language Processing > Applications > Summarization Deep Learning > Models > Transformers Deep Learning > Techniques > Fine-Tuning Deep Learning > Learning Types > Multi-Task Learning

Keywords

multi-task learning extractive summarization document summarization text summarization bert model scientific document abstractive summarization document structure bart model
Download PDF

Related papers

Fast semantic parsing with well-typedness guarantees 2020
Detecting Objectifying Language in Online Professor Reviews 2020
Analogous Process Structure Induction for Sub-event Sequence Prediction 2020
Aspect Sentiment Classification with Aspect-Specific Opinion Spans 2020
Robust and Interpretable Grounding of Spatial References with Relation Networks 2020