de.julielab » jcore-iexml-consumer
Generates stand-off IEXML files as used in the Mantra challenge.
更新时间: 2022-12-18 23:50de.julielab » jcore-topics-writer
Writes the topic weights, given the jcore-topic-indexing-ae running before, into a simple text file. Thus, the output consists of a sequency of double numbers encodes as strings, separated by tab characters. The topic ID is just the 0-based index of each number, from left to right in the written file. The first entry of each file is the document ID.
更新时间: 2022-12-18 23:49de.julielab » jcore-acronym-ae
Arconym Tagger based on the SCHWARTZ & HEARST Algorithm: Ariel S. Schwartz and Marti A. Hearst: A Simple Algorithm For Identifying Abbreviation Definitions in Biomedical Text. In: Pacific Symposium on Biocomputing, 2003.
更新时间: 2022-12-18 23:49de.julielab » jcore-annotation-removal-ae
Removes annotations from the CAS that belong to one of the types specified as a parameter value in the descriptor.
更新时间: 2022-12-18 23:49de.julielab » jcore-ign-reader
Collection Reader for the IGN corpus in BioC format as accessible at https://sites.google.com/site/hongjiedai/projects/the-ign-corpus.
更新时间: 2022-12-18 23:49de.julielab » jcore-coordination-baseline-ae
This is a baseline approach to the Coordination Resolution problem. It is used in our jcore-coordination-ae, that is only accessible on GitHub due to being in an unfinished state.
更新时间: 2022-12-18 23:49de.julielab » jcore-mstparser-ae
Slightly modified version of the MST parser to fit into the UIMA framework. This dependency parser determines all syntactic dependencies between words within a sentence. Certain level of adaptation of the original source code was necessary to neatly integrate the parser in UIMA.
更新时间: 2022-12-18 23:49de.julielab » jcore-opennlp-sentence-ae-medical-german
This Model was trained on the confidential FraMed corpus.
更新时间: 2022-12-18 23:44de.julielab » jcore-medline-db-reader
An instantiation of the jcore-db-reader that uses the jcore-xml-mapper to retrieve and parse MEDLINE XML from a PostgreSQL database. The XML format of retrieved documents is expected to follow the MEDLINE XML schema that was used until inclusive 2016. I.e. the root element of MEDLINE documents must be MedlineCitation and not, as it is since 2017, PubmedArticle.
更新时间: 2022-12-18 23:44de.julielab » jcore-jpos-ae-medical-german
This project employs the jcore-jpos-ae (Part-of-Speech Tagger) with a model trained on the confidential FraMed corpus.
更新时间: 2022-12-18 23:43de.julielab » jcore-linnaeus-species-ae-genera-species-proxies-dicts
This project is a resource for the JCoRe Linnaeus Annotator. The dictionaries contained herein are used for the recognition of concrete species names in text, e.g. "human", "mouse", "n. furzeri", "c. elegans" etc as well as species hints, i.e. indirect clues to a species like the word "patient" which most likely refers to a human. Additionally to such rather clear proxies, this project also includes a small dictionary containing maximum-frequency-proxies for genus expressions like "Drosophila" which will be mapped to "D. melanogaster". For the task of only finding concrete species names in text, there is the project jcore-linnaeus-species-ae-species-dict.
更新时间: 2022-12-18 23:43de.julielab » jcore-pubmed-reader
Leveraging the JCoRe XML Reader, this project employs a PubMed-enabled mapping file to map PubMed XML documents to CAS instances. The input is a directory of single XML files, each containing exactly one XML PubmedArticle. The XML format is the one used by NCBI when displaying results in PubMed as XML.
更新时间: 2022-12-18 23:43仓库 | 个数 |
Central | 592045 |