139,068 Hits in 4.1 sec

Automatically assigning research methods to journal articles in the domain of social sciences

Judith Eckle-Kohler, Tri-Duc Nghiem, Iryna Gurevych
2013 Proceedings of the American Society for Information Science and Technology  
The multi-label classification system we present uses only abstracts and titles of journal articles as input.  ...  Our classification approach could be applied to automatically analyze large publications databases and databases of bibliographic references according to the use of empirical and quantitative empirical  ...   Which features are most important when classifying papers based on their abstracts: textual features or metadata features?  ... 
doi:10.1002/meet.14505001049 fatcat:e5rbzoedjzg5xbwxxhdwtjsige

Capturing Interdisciplinarity in Academic Abstracts

Federico Nanni, Laura Dietz, Stefano Faralli, Gloran Glavaš, Simone Paolo Ponzetto
2016 D-Lib Magazine  
publications be predicted using supervised models with content-based features?  ...  using directly the same lexical and semantic features ( orig ) that were used for the main discipline classifier.  ... 
doi:10.1045/september2016-nanni fatcat:5mve2bsf5rdt3kvn2ncfia3dkq

Improving Scholarly Knowledge Representation: Evaluating BERT-based Models for Scientific Relation Classification [article]

Ming Jiang, Jennifer D'Souza, Sören Auer, J. Stephen Downie
2020 arXiv   pre-print
With the rapid growth of research publications, there is a vast amount of scholarly knowledge that needs to be organized in digital libraries.  ...  Within such graph-based pipelines, inferring relation types between related scientific concepts is a crucial step.  ...  Related Work Relations Mined from Scientific Publications.  ... 
arXiv:2004.06153v2 fatcat:sr44tjxh4fdz7bhxqbfps6uu6e

Integrating image caption information into biomedical document classification in support of biocuration

2020 Database: The Journal of Biological Databases and Curation  
The proposed framework used a variety of features obtained from the different parts of the publication to assess the impact of using captions vs. title-and-abstracts only.  ...  In the experiments where we use only the title and the abstract for training/testing the base-classifier, the number of features selected is ∼5000, while the number of features identified when we use image  ... 
doi:10.1093/database/baaa024 pmid:32294192 pmcid:PMC7159034 fatcat:btqaznfepncutewhzeebithgnu

Classifying Biomedical Text Abstracts Based On Hierarchical 'Concept' Structure

Rozilawati Binti Dollah, Masaki Aono
2011 Zenodo  
In this paper, we present an approach for classifying a collection of biomedical text abstracts downloaded from Medline database with the help of ontology alignment.  ...  Classifying biomedical literature is a difficult and challenging task, especially when a large number of biomedical articles should be organized into a hierarchical structure.  ...  However, in our research, we explore the use of hierarchical structure or ontology for classifying biomedical text abstracts.  ... 
doi:10.5281/zenodo.1080995 fatcat:zjjn3mx6z5ax5jkvvxl72w5suq

Venue Classification of Research Papers in Scholarly Digital Libraries [chapter]

Cornelia Caragea, Corina Florescu
2018 Lecture Notes in Computer Science  
The venue of publication is another important aspect about a scientific paper, which reflects its authoritativeness. However, the venue is not always readily available for a paper.  ...  We explore a supervised learning approach to automatically classifying the venue of a research paper using information solely available from the content of the paper and show experimentally on a dataset  ...  Features Classifier Table 2 : Comparison of features extracted from title + abstract and references list.  ... 
doi:10.1007/978-3-030-00066-0_11 fatcat:kigj6xmdjfcfthupc6msrt7poa

Machine learning misclassification of academic publications reveals non-trivial interdependencies of scientific disciplines

Alexey Lyutov, Yilmaz Uygun, Marc-Thorsten Hütt
2020 Scientometrics  
to scientific disciplines—based on the information contained in the abstract.  ...  between misclassification and citation frequencies, and (3) allows disciplines to be classified as 'method lenders' and 'content explorers', based on their in-degree out-degree asymmetry.  ...  Their explosion in the last years enables us to draw a map of science from a novel perspective, namely by assessing how machines classify abstracts of scientific publications into the categories of a journal  ... 
doi:10.1007/s11192-020-03789-8 fatcat:zeo7eatn5rfmhpwgpcbl4vibdq

Supporting the Curation of Biological Databases with Reusable Text Mining

Olivo Miotto, Tin Wee Tan, Vladimir Brusic
2005 Genome Informatics Series  
We tested the performance of two different classifier algorithms (CART and ANN), applied to both composite and single-word features, using several feature scoring functions.  ...  Curators of biological databases transfer knowledge from scientific publications, a laborious and expensive manual process.  ...  (A) Classifier Performance using Composite Features (B) Classifier Performance using Single Word Features  ... 
doi:10.11234/gi1990.16.2_32 fatcat:ptmmatc3bfdbzgcpc47y3i2sze

Classifying Negative Findings in Biomedical Publications

Bei Yu, Daniele Fanelli
2014 Proceedings of BioNLP 2014  
Using multinomial naïve Bayes algorithm and bag-ofwords features enriched by parts-ofspeeches and constituents, we built a classifier that reached 84% accuracy based on 5-fold cross validation on a balanced  ...  This paper proposes an NLP approach for automatically classifying negated sentences in biomedical abstracts as either reporting negative findings or not.  ...  The best classifier was built using MNB and bag-of-words features enriched with PoS tags and constituent markers.  ... 
doi:10.3115/v1/w14-3403 dblp:conf/bionlp/YuF14 fatcat:q4wxb7nfwfhohl5auck6e7rbha

Automatic Identification of Recent High Impact Clinical Articles in PubMed to Support Clinical Decision Making Using Time-agnostic Features

Jiantao Bian, Samir Abdelrahman, Jianlin Shi, Guilherme Del Fiol
2018 Journal of Biomedical Informatics  
Using a gold standard of 541 high impact treatment studies referenced in 11 disease management guidelines, we tested the following null hypotheses: 1) the high impact classifier with time-agnostic features  ...  To identify recent studies, we developed our classification model using time-agnostic features that are available as soon as an article is indexed in PubMed®, such as journal impact factor, author count  ...  Mork in the National Library of Medicine (NLM) for processing our initial dataset using NLM Medical Text Indexer (MTI).  ... 
doi:10.1016/j.jbi.2018.11.010 pmid:30468912 pmcid:PMC6342626 fatcat:256u3rzvojax3m5klgmcp3dkg4

Using argumentation to retrieve articles with similar citations: An inquiry into improving related articles search in the MEDLINE digital library

2006 International Journal of Medical Informatics  
A Bayesian classifier trained on explicitly structured MEDLINE abstracts generates these argumentative categories. The categories are used to generate four different argumentative indexes.  ...  The aim of this study is to investigate the relationships between citations and the scientific argumentation found in the abstract.  ...  Introduction Numerous techniques help researchers locate relevant documents in an ever-growing mountain of scientific publications.  ... 
doi:10.1016/j.ijmedinf.2005.06.007 pmid:16165395 fatcat:rxdsamwfprhshfccpxghwd4w7a

Identification of abstract features presented at the combined otolaryngology spring meeting predicting publication in impactful peer‐reviewed journals

Fatma S. Genc, Christopher D. Dwyer, David E. Rosow, Steven D. Stockton, VyVy N. Young, Clark A. Rosen
2021 Laryngoscope Investigative Otolaryngology  
Review abstracts presented at the Combined Otolaryngology Society Meeting (COSM) to determine subsequent publication and identify abstract features predictive of publication in high impact journals.  ...  The Journal of Citation Reports was used to determine impact factors for published abstracts.  ...  Ideally, it would be useful to know of specific abstract features that predict subsequent publication, preferentially in high impact journals.  ... 
doi:10.1002/lio2.592 pmid:34401488 pmcid:PMC8356865 fatcat:aoqxzbx5afgxzlhpcei525e4ka

Multimodal Approach for Metadata Extraction from German Scientific Publications [article]

Azeddine Bouabdallah, Jorge Gavilan, Jennifer Gerbl, Prayuth Patumcharoenpol
2021 arXiv   pre-print
German scientific papers come in a large variety of layouts which makes the extraction of metadata a non-trivial task that requires a precise way to classify the metadata extracted from the documents.  ...  It enables the utilization of both spatial and contextual features in order to achieve a more reliable extraction.  ...  However, these approaches were designed to tackle English scientific papers. The issue lies with German scientific publications [5] .  ... 
arXiv:2111.05736v1 fatcat:rz5xwg5nkrhz7hwn54by2eqcpa

Towards Automatic Recognition of Scientifically Rigorous Clinical Research Evidence

H. Kilicoglu, D. Demner-Fushman, T. C. Rindflesch, N. L. Wilczynski, R. B. Haynes
2009 JAMIA Journal of the American Medical Informatics Association  
studies, with stacking over five feature-classifier combinations and 82.5% precision and 84.3% recall in recognizing rigorous studies with treatment focus using stacking over word ϩ metadata feature vector  ...  We identify scientifically rigorous studies using supervised machine learning techniques (Naïve Bayes, support vector machine (SVM), and boosting) trained on high-level semantic features.  ...  Their feature set exploits MeSH indexing terms and publication types assigned by NLM indexers as well as words in the title and abstract of the citation.  ... 
doi:10.1197/jamia.m2996 pmid:18952929 pmcid:PMC2605595 fatcat:mvgjn426qngi3lqvbgbla4aloq

MexPub: Deep Transfer Learning for Metadata Extraction from German Publications [article]

Zeyd Boukhers and Nada Beili and Timo Hartmann and Prantik Goswami and Muhammad Arslan Zafar
2021 arXiv   pre-print
However, this does not apply to German scientific publications, which have a variety of styles and layouts.  ...  In contrast to most of the English scientific publications that follow standard and simple layouts, the order, content, position and size of metadata in German publications vary greatly among publications  ...  Therefore, most of the earlier works addressed the problem of classifying segment strings in scientific documents using context-based classifiers such as Hidden Markov Models (HMMs) [26] and Conditional  ... 
arXiv:2106.07359v1 fatcat:k5446qbqvzhonj32urjqvaagpq
« Previous Showing results 1 — 15 out of 139,068 results