Automatic summarization of scientific publications using a feature selection approach

Saied, Hazem Al; Dugué, Nicolas; Lamirel, Jean–Charles

doi:10.1007/s00799-017-0214-x

Cited by 10 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each section in the document is represented as a vector, with words or expressions being the features of this vector. Feature maximization detects the specific features that describe each section and discriminate it from the others [71]. The Feature Fmeasure of each word is calculated after removing the stop words.…”

Section: Unsupervised Approachesmentioning

confidence: 99%

Survey of Scientific Document Summarization Techniques

K¹,

Mathew²

2020

csci

View full text Add to dashboard Cite

The number of scientic or research papers published every year is growing at an exponential rate, which has led to an intensive research in scientic document summarization. The different methods commonly used in automatic text summarization are discussed in this paper with their pros and cons. Commonly used evaluation techniques and datasets in this field are also discussed. Rouge and Pyramid scores of the different methods are tabulated for easy comparison of the results.

show abstract

Section: Unsupervised Approachesmentioning

confidence: 99%

Survey of Scientific Document Summarization Techniques

K¹,

Mathew²

2020

csci

View full text Add to dashboard Cite

show abstract

“…2 This special issue resulting from the BIRNDL workshop includes 14 papers: four extended papers presented at the first BIRNDL workshop and the BIR workshop at ECIR 2016 [2,8,14,18], three extended system reports of the CL-SciSumm Shared Task 2016 [1,13,16] and one overview paper [11] and six original research papers submitted via the open call for papers [6,7,9,10,12,17]. guage Processing publications" [14] to detect extrinsic instances of self-reuse, self-plagiarism, reuse and plagiarism in NLP and speech processing articles.…”

Section: Special Issue Papersmentioning

confidence: 99%

“…Furthermore, they demonstrate how topic models can better represent the limited vocabulary of citances and lead to better performances in the citation-mapping task. -Al Saied et al's "Automatic summarization of scientific publications using a feature selection approach" [1] explores the flexibility and relevance of an optimized, language-agnostic feature-based approach, evaluated both on the DUC ACQUAINT corpus and the SciSumm corpus. Its strongest advantage is that it is not dependent on the availability of a training set.…”

Section: Cl-scisumm Shared Task System Trackmentioning

confidence: 99%

Introduction to the special issue on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL)

et al. 2017

View full text Add to dashboard Cite

The large scale of scholarly publications poses a challenge for scholars in information seeking and sensemaking. Bibliometric, information retrieval (IR), text mining, and natural language processing techniques can assist to address this challenge, but have yet to be widely used in digital libraries (DL). This special issue on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL) was compiled after the first joint BIRNDL workshop that was held at the joint conference on digital libraries (JCDL 2016) in Newark, New Jersey, B Philipp Mayr

show abstract

“…Different summarization solutions have been proposed in the literature, including the automated generation of text summaries using computational linguistic techniques [ 6 ]. Another popular approach is that based on “word cloud” representations [ 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

PMIDigest: Interactive Review of Large Collections of PubMed Entries to Distill Relevant Information

Novoa

Chagoyen

Benito

et al. 2023

Genes

View full text Add to dashboard Cite

Scientific knowledge is being accumulated in the biomedical literature at an unprecedented pace. The most widely used database with biomedicine-related article abstracts, PubMed, currently contains more than 36 million entries. Users performing searches in this database for a subject of interest face thousands of entries (articles) that are difficult to process manually. In this work, we present an interactive tool for automatically digesting large sets of PubMed articles: PMIDigest (PubMed IDs digester). The system allows for classification/sorting of articles according to different criteria, including the type of article and different citation-related figures. It also calculates the distribution of MeSH (medical subject headings) terms for categories of interest, providing in a picture of the themes addressed in the set. These MeSH terms are highlighted in the article abstracts in different colors depending on the category. An interactive representation of the interarticle citation network is also presented in order to easily locate article “clusters” related to particular subjects, as well as their corresponding “hub” articles. In addition to PubMed articles, the system can also process a set of Scopus or Web of Science entries. In summary, with this system, the user can have a “bird’s eye view” of a large set of articles and their main thematic tendencies and obtain additional information not evident in a plain list of abstracts.

show abstract

Automatic summarization of scientific publications using a feature selection approach

Cited by 10 publications

References 15 publications

Survey of Scientific Document Summarization Techniques

Survey of Scientific Document Summarization Techniques

Introduction to the special issue on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL)

PMIDigest: Interactive Review of Large Collections of PubMed Entries to Distill Relevant Information

Contact Info

Product

Resources

About