SAPIENTA
Automating the Semantic Annotation of PapersSAPIENT Automation aims to help researchers process scientific papers faster and get the information they are interested in out of them. The project achieves this by automating the recognition of core scientific concepts such as Motivation, Method, Result, Conclusion in papers and uses them to generate automatic summaries.
-
Multi-label Annotation in Articles
27 May 2016 11:47 -
Automatic classification of paper types
12 December 2013 11:57 -
CoreSC automation and Extractive summaries
7 October 2011 10:45
- SAPIENTA Web service
The latest version of SAPIENTA, usable as a Webservice. - SAPIENTA FAQ
Installing, running and troubleshooting SAPIENTA - Latest binary version of SAPIENTA
Download SAPIENTA for Firefox 3 or Firefox 4 and later. - SSSplit
XML-aware sentence splitter. Requires Java 1.6 or later. - Example files for use with SAPIENTA, SSSplit and SAPIENT
- Multi-label Annotation in Scientific Articles – The Multi-label Cancer Risk Assessment Corpus
Published in LREC 2016 - Partridge: An Effective System for the Automatic Classification of the Types of Academic Papers
Paper published in AI-SGAI 2013 - A discourse-driven content model for summarising scientific articles evaluated in a complex question answering task
Paper published in EMNLP 2013
- Multi-CoreSC CRA corpus (MCCRA)
50 papers annotated with multiple CoreSC labels per sentence. - Multi-CoreSC Annotation Guidelines
- The ART Corpus
265 papers annotated with core scientific concepts - Easily browsable ART corpus
HTML version of the ART corpus - Dr Maria Liakata
Principal investigator for the SAPIENTA project
