1,638 Hits in 5.6 sec

Incorporating Figure Captions and Descriptive Text in MeSH Term Indexing

Xindi Wang, Robert E. Mercer
2019 Proceedings of the 18th BioNLP Workshop and Shared Task  
Beyond the normal use of the text from the abstract and title for model training, we also consider figure and table captions, as well as paragraphs associated with the figures and tables.  ...  In this paper, we focus specifically on biomedical document classification using a deep learning approach. We present a novel multichannel TextCNN model for MeSH term indexing.  ...  Acknowledgements This research is partially funded by The Natural Sciences and Engineering Research Council of Canada through a Discovery Grant to Robert E. Mercer.  ... 
doi:10.18653/v1/w19-5018 dblp:conf/bionlp/WangM19 fatcat:k2arbfqqq5b3nokdcy75nxiira

Automated Semantic Indexing of Figure Captions to Improve Radiology Image Retrieval

C. E. Kahn, D. L. Rubin
2009 JAMIA Journal of the American Medical Informatics Association  
Conclusion: Concept-based indexing of radiology journal figure captions achieved very high precision and recall, and significantly improved image retrieval.  ...  Design: The MetaMap Transfer program (MMTx) was used to map the text of 84,846 figure captions from 9,004 peer-reviewed, English-language articles to concepts in three controlled vocabularies from the  ...  Conceptual indexing differs from keyword indexing in that the text is labeled with descriptive terms, usually taken from a controlled terminology.  ... 
doi:10.1197/jamia.m2945 pmid:19261938 pmcid:PMC2732225 fatcat:jvo3am2fc5di7emgqomdrrsr5m

MeSHup: A Corpus for Full Text Biomedical Document Indexing [article]

Xindi Wang, Robert E. Mercer, Frank Rudzicz
2022 arXiv   pre-print
We release a large scale annotated MeSH indexing corpus, MeSHup, which contains 1,342,667 full text articles in English, together with the associated MeSH labels and metadata, authors, and publication  ...  Medical Subject Heading (MeSH) indexing refers to the problem of assigning a given biomedical document with the most relevant labels from an extremely large set of MeSH terms.  ...  Acknowledgements We thank all reviewers for their constructive comments and feedback. Resources used in preparing this research were provided, in part, by Compute Ontario  ... 
arXiv:2204.13604v1 fatcat:srvmuhrgjbb4nnysru2xhkzouy

Improving image retrieval effectiveness via query expansion using MeSH hierarchical structure

Mariano Crespo Azcárate, Jacinto Mata Vázquez, Manuel Maña López
2013 JAMIA Journal of the American Medical Informatics Association  
In order to achieve greater effectiveness in the expansion, the search text was analyzed to identify which terms were most amenable to being expanded.  ...  In the second strategy the text of the query was divided into n-grams, resulting in sequences corresponding to MeSH descriptors.  ...  title text, figure captions, abstracts or full text.  ... 
doi:10.1136/amiajnl-2012-000943 pmid:22952301 pmcid:PMC3822102 fatcat:jq376vzfwzefrmzeqaodqv4wfu

Design and Development of a Multimodal Biomedical Information Retrieval System

Dina Demner-Fushman, Sameer Antani, Matthew Simpson, George R. Thoma
2012 Journal of Computing Science and Engineering  
Biomedical information exists in different forms: as text and illustrations in journal articles and other documents, in images stored in databases, and as patients' cases in electronic health records.  ...  This paper presents ways to move beyond conventional text-based searching of these resources, by combining text and visual features in search queries and document representation.  ...  We thank Essie developers Russell Loane and Nicholas Ide for providing the search engine, and being wonderfully responsive and supportive in development of the OpenI systems.  ... 
doi:10.5626/jcse.2012.6.2.168 fatcat:am3nzm4djfft5g5ngklp6fjmae

Semedico: A Comprehensive Semantic Search Engine for the Life Sciences

Erik Faessler, Udo Hahn
2017 Proceedings of ACL 2017, System Demonstrations  
SEMEDICO excels with an ad-hoc search approach which directly reflects relevance in terms of information density of entities and relations among them (events) and, a truly unique feature, ranks interaction  ...  SEMEDICO is a semantic search engine designed to support literature search in the life sciences by integrating the semantics of the domain at all stages of the search process-from query formulation via  ...  captions and the complete document text, if applicable.  ... 
doi:10.18653/v1/p17-4016 dblp:conf/acl/FaesslerH17 fatcat:folqg7czdbdsdo5z6uqfnw2e5a

Multi-Attention and Incorporating Background Information Model for Chest X-Ray Image Report Generation

Xin Huang, Fengqi Yan, Wei Xu, Maozhen Li
2019 IEEE Access  
INDEX TERMS Attention mechanism, deep learning, radiology report generation, word embedding. 154808 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  Chest X-ray images are widely used in clinical practice such as diagnosis and treatment.  ...  IMAGE CAPTIONING Image Captioning is a task that automatically generates text descriptions for given images.  ... 
doi:10.1109/access.2019.2947134 fatcat:mynqvu4r5fdcrj5utuplhodxkq

ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic [article]

Yoad Tewel, Yoav Shalev, Idan Schwartz, Lior Wolf
2022 arXiv   pre-print
In this work, we repurpose such models to generate a descriptive text given an image at inference time, without any further training or tuning steps.  ...  Moreover, as a zero-shot learning method, it is extremely flexible and we demonstrate its ability to perform image arithmetic in which the inputs can be either images or text, and the output is a sentence  ...  Moreover, the semantic knowledge incorporated into CLIP and GPT-2 is manifested in the resulting caption, see Fig. 1 .  ... 
arXiv:2111.14447v2 fatcat:vfowvq2qofbt3aef4l5swdanum

Information Retrieval by Semantic Similarity

Angelos Hliaoutakis, Giannis Varelas, Epimenidis Voutsakis, Euripides G.M. Petrakis, Evangelos Milios
2006 International Journal on Semantic Web and Information Systems (IJSWIS)  
Typically, semantic similarity is computed by mapping terms to an ontology and by examining their relationships in that ontology.  ...  The most popular semantic similarity methods are implemented and evaluated using WordNet and MeSH.  ...  All OHSUMED documents are indexed by title, abstract and MeSH terms (MeSH Headings).  ... 
doi:10.4018/jswis.2006070104 fatcat:txa6cg4rwnejdgpkuw7giq3nf4

The Transcription Factor Encyclopedia

Dimas Yusuf, Stefanie L Butland, Magdalena I Swanson, Eugene Bolotin, Amy Ticoll, Warren A Cheung, Xiao Cindy Zhang, Christopher TD Dickman, Debra L Fulton, Jonathan S Lim, Jake M Schnabl, Oscar HP Ramos (+102 others)
2012 Genome Biology  
TFe aims to rapidly educate scientists about the TFs they encounter through the delivery of succinct summaries written and vetted by experts in the field. TFe is available at  ...  Notable features of the TFe website include a high-quality PDF generator and web API for programmatic data retrieval.  ...  Computer hardware resources utilized in this project were supported by the Gene Regulation Bioinformatics Laboratory funded by the Canada Foundation for Innovation (CFI).  ... 
doi:10.1186/gb-2012-13-3-r24 pmid:22458515 pmcid:PMC3439975 fatcat:gxpf77o6urfddir5vw7igipj3a

Frontiers of biomedical text mining: current progress

P. Zweigenbaum, D. Demner-Fushman, H. Yu, K. B. Cohen
2007 Briefings in Bioinformatics  
It is now almost 15 years since the publication of the first paper on text mining in the genomics domain, and decades since the first paper on text mining in the medical domain.  ...  Some problems, such as abbreviationhandling, can essentially be considered solved problems, and others, such as identification of gene mentions in text, seem likely to be solved soon.  ...  KBC was supported by NIH grants 'Construction of a Full Text Corpus for Biomedical Text Mining' (#1G08LM009639-01) and 'Technology Development for a Molecular Biology Knowledge-base' (#5R01 LM008111-03  ... 
doi:10.1093/bib/bbm045 pmid:17977867 pmcid:PMC2516302 fatcat:4nfbokb7lfdjbnkijw2v6754qy

A Sparse Transformer-Based Approach for Image Captioning

Congcong Zhou, Zhou Lei, Shengbo Chen, Yiyong Huang, Xianrui Liu
2020 IEEE Access  
INDEX TERMS Image captioning, self-attention, explict sparse, local adaptive threshold.  ...  Image Captioning is the task of providing a natural language description for an image.  ...  ACKNOWLEDGMENT The authors would like to thank the High Performance Computing Center of Shanghai University for providing the computing resources and technical support.  ... 
doi:10.1109/access.2020.3024639 fatcat:j2wcwshcqrhe3oxzkiylq5wzcq

Geometry Attention Transformer with Position-aware LSTMs for Image Captioning [article]

Chi Wang, Yulin Shen, Luping Ji
2021 arXiv   pre-print
steps, and 2) a group of position-LSTMs, for precisely informing the decoder of relative word position in generating caption texts.  ...  In recent years, transformer structures have been widely applied in image captioning with impressive performance.  ...  Figure 3 : 3 The output comparison of captions generated respectively by our GAT and a base model, as well as three manual description captions of ground truth, GT1∼GT3.  ... 
arXiv:2110.00335v1 fatcat:emucqxpc3rdfpeu3xoewpwuj2i

GeneView: a comprehensive semantic search engine for PubMed

P. Thomas, J. Starlinger, A. Vowinkel, S. Arzt, U. Leser
2012 Nucleic Acids Research  
Research results are primarily published in scientific literature and curation efforts cannot keep up with the rapid growth of published literature.  ...  The plethora of knowledge remains hidden in large text repositories like MEDLINE. Consequently, life scientists have to spend a great amount of time searching for specific information.  ...  ACKNOWLEDGEMENTS We thank the reviewers for their careful reading and helpful comments.  ... 
doi:10.1093/nar/gks563 pmid:22693219 pmcid:PMC3394277 fatcat:pdmdg5hdbvb4reroht5v6pzlsy

Figure-Associated Text Summarization and Evaluation

Balaji Polepalli Ramesh, Ricky J. Sethi, Hong Yu, Indra Neil Sarkar
2015 PLoS ONE  
, and generate a text summary for every figure in an article.  ...  Biomedical literature incorporates millions of figures, which are a rich and important knowledge resource for biomedical researchers.  ...  [56] developed a method that computes similarities between the MeSH terms assigned to an article in addition to its word tokens and then returns the top N-ranked sentences as summary sentences.  ... 
doi:10.1371/journal.pone.0115671 pmid:25643357 pmcid:PMC4313946 fatcat:dbkj7zhyq5bmjkkhfdnef2wpne
« Previous Showing results 1 — 15 out of 1,638 results