A Summarization System for Scientific Documents

Erera, Shai; Shmueli-Scheuer, Michal; Feigenblat, Guy; Nakash, Ora Peled; Boni, Odellia; Roitman, Haggai; Cohen, Doron; Weiner, Bar; Mass, Yosi; Rivlin, Or; Lev, Guy; Jerbi, Achiya; Herzig, Jonathan; Hou, Yufang; Jochim, Charles; Gleize, Martin; Bonin, Francesca; Konopnicki, David

doi:10.48550/arxiv.1908.11152

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lloret et al [72], Qazvinian et al [89], Qazvinian and Radev [90], Saggion and Lapalme [98], Slamet et al [101], Teufel and Moens [108]) and multi-document summarization (e.g. Erera et al [31], Khodral et al [55], Mohammad et al [78]). Single document summarization generates a summary of a single paper, while multidocument summarization summarizes a set of papers belonging to the same topic jointly in a single summary, which is more challenging than the single document case.…”

Section: Prior Workmentioning

confidence: 99%

Automatic Related Work Generation: A Meta Study

Li¹,

Ouyang²

2022

Preprint

View full text Add to dashboard Cite

Academic research is an exploration activity to solve problems that have never been resolved before. By this nature, each academic research work is required to perform a literature review to distinguish its novelties that have not been addressed by prior works. In natural language processing, this literature review is usually conducted under the "Related Work" section. The task of automatic related work generation aims to automatically generate the "Related Work" section given the rest of the research paper and a list of cited papers. Although this task was proposed over 10 years ago, it received little attention until very recently, when it was cast as a variant of the scientific multi-document summarization problem. However, even till today, the problems of automatic related work and citation text generation are not yet standardized. In this survey, we conduct a meta-study to compare the existing literature on related work generation from the perspectives of problem formulation, dataset collection, methodological approach, performance evaluation, and future prospects to provide the reader insight into the progress of the state-of-the-art studies, as well as and how future studies can be conducted. We also survey relevant fields of study that we suggest future work to consider integrating.

show abstract