2020

TLDR: Extreme Summarization of Scientific Documents

Cachola, Isabel, Lo, Kyle, Cohan, Arman et al.

Understand

We introduce TLDR generation, a new form of extreme summarization, for scientific papers.

TLDR generation involves high source compression and requires expert background knowledge and understanding of complex domain-specific language.
To facilitate study on this task, we introduce SciTLDR, a new multi-target dataset of 5.4K TLDRs over 3.2K papers.
SciTLDR contains both author-written and expert-derived TLDRs, where the latter are collected using a novel annotation protocol that produces high-quality summaries while minimizing annotation burden.

Built on

Roberta: A robustly optimized bert pretraining approach
Original
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019 · 1907
Earlier work this paper cites.
CTRL: A Conditional Transformer Language Model for Controllable Generation
Original
Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney, Caiming Xiong, and Richard Socher. 2019 · 1909
Earlier work this paper cites.
Pegasus: Pre-training with extracted gap-sentences for abstractive summarization
Original
Jingqing Zhang, Yao Zhao, Mohammad Saleh, and Peter J. Liu. 2019 · 1912
Earlier work this paper cites.
A simple sequentially rejective multiple test procedure
Sture Holm. 1979 · 1979
Earlier work this paper cites.
Fast generation of abstracts from general domain text corpora by extracting relevant sentences
Klaus Zechner. 1996 · 1996
Earlier work this paper cites.
Argumentative zoning information extraction from scientific text
S. Teufel. 1999 · 1999
Earlier work this paper cites.
Unilmv2: Pseudo-masked language models for unified language model pre-training
Original
Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiulei Liu, Yu Wang, Songhao Piao, Jianfeng Gao, Ming Zhou, and Hsiao-Wuen Hon. 2020 · 2002
Earlier work this paper cites.
Cbag: Conditional biomedical abstract generation
Original
Justin Sybrandt and Ilya Safro. 2020 · 2002
Earlier work this paper cites.
An introduction to duc 2003: Intrinsic evaluation of generic news text summarization systems
Paul Over. 2003 · 2003
Earlier work this paper cites.
Palm: Pre-training an autoencoding and autoregressive language model for context-conditioned generation
Original
Bin Bi, Chenliang Li, Chen Wu, Ming Yan, and Wei Wang. 2020 · 2004
Earlier work this paper cites.
Self-supervised and controlled multi-document opinion summarization
Original
Hady ElSahar, Maximin Coavoux, Matthias Gallé, and Jos Rozen. 2020 · 2004
Earlier work this paper cites.
The effects of human variation in DUC summarization evaluation
Donna Harman and Paul Over. 2004 · 2004
Earlier work this paper cites.
Conditional augmentation for aspect term extraction via masked sequence-to-sequence generation
Original
Kun Li, Chengbo Chen, Xiaojun Quan, Qing Ling, and Yan Song. 2020 · 2004
Earlier work this paper cites.
ROUGE: A package for automatic evaluation of summaries
Chin-Yew Lin. 2004 · 2004
Earlier work this paper cites.
Textrank: Bringing order into texts
Rada Mihalcea and Paul Tarau. 2004 · 2004
Earlier work this paper cites.
Evaluating content selection in summarization: The pyramid method
Ani Nenkova and Rebecca J Passonneau. 2004 · 2004
Earlier work this paper cites.
The new york times annotated corpus.(october 2008). ldc catalog no.: Ldc2008t19
Evan Sandhaus. 2008 · 2008
Earlier work this paper cites.
Using citations to generate surveys of scientific paradigms
Saif M. Mohammad, Bonnie J. Dorr, Melissa Egan, Ahmed Hassan Awadallah, Pradeep Muthukrishnan, Vahed Qazvinian, Dragomir R. Radev, and David M. Zajic. 2009 · 2009
Earlier work this paper cites.

Similar

Nouveau-rouge: A novelty metric for update summarization
John M Conroy, Judith D Schlesinger, and Dianne P O’Leary. 2011 · 2011
Cited alongside, same era.
Generating extractive summaries of scientific paradigms
Vahed Qazvinian, Dragomir R. Radev, Saif M. Mohammad, Bonnie J. Dorr, David M. Zajic, Michael Whidby, and Taesun Moon. 2013 · 2013
Cited alongside, same era.
Global scientific output doubles every nine years
Richard Van Noorden. 2014 · 2014
Cited alongside, same era.
Scientific article summarization using citation-context and article’s discourse structure
Arman Cohan and Nazli Goharian. 2015 · 2015
Cited alongside, same era.
Teaching machines to read and comprehend
Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. 2015 · 2015
Cited alongside, same era.
Surveyor: A system for generating coherent survey articles for scientific topics
Rahul Jha, Reed Coke, and Dragomir R. Radev. 2015 · 2015
Cited alongside, same era.
Revisiting summarization evaluation for scientific articles
Original
Arman Cohan and Nazli Goharian. 2016 · 2016
Cited alongside, same era.
Insights from cl-scisumm 2016: the faceted scientific document summarization shared task
Kokil Jaidka, Muthu Kumar Chandrasekaran, Sajal Rustagi, and Min-Yen Kan. 2018 · 2016
Cited alongside, same era.
Scientific document summarization via citation contextualization and scientific discourse
Arman Cohan and Nazli Goharian. 2017 · 2017
Cited alongside, same era.
A supervised approach to extractive summarisation of scientific papers
Original
Ed Collins, Isabelle Augenstein, and Sebastian Riedel. 2017 · 2017
Cited alongside, same era.
Section mixture models for scientific document summarization
John M. Conroy and Sashka Davis. 2017 · 2017
Cited alongside, same era.
Attention is all you need
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017 · 2017
Cited alongside, same era.

Then

Overview and results: Cl-scisumm shared task 2019
Muthu Kumar Chandrasekaran, Michihiro Yasunaga, Dragomir Radev, Dayne Freitag, and Min-Yen Kan. 2019 · 2019
Later among the works it cites.
Structural scaffolds for citation intent classification in scientific publications
Arman Cohan, Waleed Ammar, Madeleine van Zuylen, and Field Cady. 2019 · 2019
Later among the works it cites.
Bert: Pre-training of deep bidirectional transformers for language understanding
Original
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019 · 2019
Later among the works it cites.
Talksumm: A dataset and scalable annotation method for scientific paper summarization based on conference talks
Guy Lev, Michal Shmueli-Scheuer, Jonathan Herzig, Achiya Jerbi, and David Konopnicki. 2019 · 2019
Later among the works it cites.
Text summarization with pretrained encoders
Yang Liu and Mirella Lapata. 2019 · 2019
Later among the works it cites.
Scispacy: Fast and robust models for biomedical natural language processing
Mark Neumann, Daniel King, Iz Beltagy, and Waleed Ammar. 2019 · 2019
Later among the works it cites.
fairseq: a fast, extensible toolkit for sequence modeling
Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. 2019 · 2019
Later among the works it cites.
Green ai
Original
Roy Schwartz, Jesse Dodge, Noah A. Smith, and Oren Etzioni. 2019 · 2019
Later among the works it cites.
Bigpatent: A large-scale dataset for abstractive and coherent summarization
Eva Sharma, Chen Li, and Lu Wang. 2019 · 2019
Later among the works it cites.
“transforming” delete, retrieve, generate approach for controlled text style transfer
Akhilesh Sudhakar, Bhargav Upadhyay, and Arjun Maheswaran. 2019 · 2019
Later among the works it cites.
Extractive summarization of long documents by combining global and local context
Wen Xiao and Giuseppe Carenini. 2019 · 2019
Later among the works it cites.
Scisummnet: A large annotated corpus and content-impact models for scientific paper summarization with citation networks
Michihiro Yasunaga, Jungo Kasai, Rui Zhang, Alexander Richard Fabbri, Irene Li, Dan Friedman, and Dragomir R. Radev. 2019 · 2019
Later among the works it cites.
Sentence centrality revisited for unsupervised summarization
Hao Zheng and Mirella Lapata. 2019 · 2019
Later among the works it cites.
Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension
Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2020 · 2020
Closest in time.
S2orc: The semantic scholar open research corpus
Original
Kyle Lo, Lucy Lu Wang, Mark Neumann, Rodney Kinney, and Daniel S. Weld. 2020 · 2020
Closest in time.
Exploring the limits of transfer learning with a unified text-to-text transformer
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020 · 2020
Closest in time.
Cited text span identification for scientific summarisation using pre-trained encoders
Chrysoula Zerva, Minh-Quoc Nghiem, Nhung T. H. Nguyen, and S. Ananiadou. 2020 · 2020
Closest in time.
Extractive summarization as text matching
Ming Zhong, Pengfei Liu, Yiran Chen, Danqing Wang, Xipeng Qiu, and Xuanjing Huang. 2020 · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…