Identification of Environment Ontology terms in text and the annotation of the Encyclopedia of Life http://www.environments-eol.blogspot.com/ Evangelos Pafilis 1* , Sune Frankild 2 , Lucia Fanini 1 , Sarah Faulwetter 1 , Christina Pavloudi 1 , Julia Schnetzer 3 , Aikaterini Vasileiadou 1 , Umer Ijaz 4 , Christos Arvanitidis 1 , Robert Stevenson 5 , Lars Juhl Jensen 2, 1 HCMR, Crete, GR, 2 CPR-NNF, Copenhagen, DK, 3 MPI-MM, Bremen, DE, 4 Uni of Glasgow, UK, 5 Uni of Massachusetts, Boston, US *: pafilis@hcmr.gr, http://epafilis.info TDWG – 27 th Oct 2014 – Jönköping
Species – Environments TDWG – 27 th Oct 2014 – Jönköping
http://eol.org/ Parr CS, et al. The Encyclopedia of Life v2: Providing Global Access to Knowledge About Life on Earth (2014) Biodiversity Data Journal 2: e1079 TDWG – 27 th Oct 2014 – Jönköping
Encyclopedia of Life (EOL) http://www.eol.org • one-stop-shop for biodiversity knowledge • Over 3 Mi Taxa • http://eol.org/info/discover_what TDWG – 27 th Oct 2014 – Jönköping
Encyclopedia of Life (EOL) http://www.eol.org • one-stop-shop for biodiversity knowledge • Over 3 Mi Taxa • http://eol.org/info/discover_what TDWG – 27 th Oct 2014 – Jönköping
Species Descriptions (e.g. “Biology Description”, “Ecology”, “Habitat”) TDWG – 27 th Oct 2014 – Jönköping
Species Descriptions (e.g. “Biology Description”, “Ecology”, “Habitat”) h ttp://rs.tdwg.org/ontology/voc/SPMInfoItems# Biology http://rs.tdwg.org/ontology/voc/SPMInfoItems# Conservation http://rs.tdwg.org/ontology/voc/SPMInfoItems# Description http://rs.tdwg.org/ontology/voc/SPMInfoItems# Dispersal http://rs.tdwg.org/ontology/voc/SPMInfoItems# Distribution http://rs.tdwg.org/ontology/voc/SPMInfoItems# Ecology http://rs.tdwg.org/ontology/voc/SPMInfoItems# Habitat http://rs.tdwg.org/ontology/voc/SPMInfoItems# LifeCycle http://rs.tdwg.org/ontology/voc/SPMInfoItems# Migration http://rs.tdwg.org/ontology/voc/SPMInfoItems# Reproduction http://rs.tdwg.org/ontology/voc/SPMInfoItems# TrophicStrategy http://www.eol.org/voc/table_of_contents# Wikipedia More info: http://eol.org/info/98 (“EOL Subject Types”) TDWG – 27 th Oct 2014 – Jönköping
Information in Free Text http://eol.org/data_objects/31415353 TDWG – 27 th Oct 2014 – Jönköping
Information in Free Text http://eol.org/data_objects/31415353 TDWG – 27 th Oct 2014 – Jönköping
Information in Free Text ID: ENVO:00000192 Name: mudflat http://eol.org/data_objects/31415353 ID: ENVO:00000020 Name: lake TDWG – 27 th Oct 2014 – Jönköping
Literature Mining TDWG – 27 th Oct 2014 – Jönköping
processing text to extract facts of interest TDWG – 27 th Oct 2014 – Jönköping
terrestrial, aquatic, marine, lagoon, coral reef, sediment, freshwater, soil TDWG – 27 th Oct 2014 – Jönköping
ENVIRONMENTS TDWG – 27 th Oct 2014 – Jönköping
ENVIRONMENTS http://environments.hcmr.gr http://environments-eol.blogspot.gr/ ● Dictionary based, Open source ● E600 gold standard: EnvO-based ● Environment Ontology corpus of EOL Species pages ● fast performance ● Recognition Accuracy – Mention Level: ● 4000 PubMed abstracts / - F1: 82.0% second * 87.1% of the TPs: exact id ● Based on SPECIES name recognition among predicted ones tagger (Pafilis et al , PLOS ONE) Pafilis E et al . (2013) The SPECIES and ORGANISMS Resources for Fast and Accurate Identification of Taxonomic Names in Text. PLoS ONE 8(6): e65390 *: based a single-thread run on an Intel 2,27GHz, 24 GB RAM processing a set of 536,052 abstracts TDWG – 27 th Oct 2014 – Jönköping
EnvO: source of environment descriptor names and synonyms … biome … environmental feature … environmental material … environmental condition http://environmentontology.org … ~1600 terms, June 2013 habitat Based on slides by Dr. Pier Luigi Buttigier, AWI, Bremenhaven, Germany TDWG – 27 th Oct 2014 – Jönköping
ENVIRONMENTS – Improving Accuracy ● Increasing matches in text ● orthographic variation supported e.g. freshwater, fresh water, and fresh-water ● Case-insensitive matching ● Synonym generation to reflect the way environment descriptive terms are mentioned in text (both generic and EnvO specific) Action Example Add a variant in which epipelagic zone → epipelagic non-informative words estuarine biome → estuarine have been removed Plural form addition sediment → sediments Adjective form addition lagoon → lagoonal ● Preventing overmatching (i.e. avoiding increased FP) ● „stopword-list” (e.g. spring, well, range) TDWG – 27 th Oct 2014 – Jönköping
Scope EnvO parts Not included: species tissues foods Limitations – Known Issues negation not supported conflicts with anatomy terms (e.g. mouth, blowhole) TDWG – 27 th Oct 2014 – Jönköping
ENVIRONMENTS – Sample Output Match End Start EnvO ID File Name text coord coord eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00000192 eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00002297 eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00000043 eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00000000 eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00000012 eol_documents_ascii_nonHTML.txt 346289871 346289873 mud ENVO:01000001 eol_documents_ascii_nonHTML.txt 346289871 346289873 mud ENVO:00010483 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000180 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000191 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00002297 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000176 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000000 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000477 Tags corresponding to “Habitat” text data object: http://eol.org/data_objects/31415353 of EOL Taxon Phoenicopterus ruber (Greater Flamingo): http://eol.org/pages/913221 TDWG – 27 th Oct 2014 – Jönköping
ENVIRONMENTS – Sample Output Match End Start EnvO ID File Name text coord coord eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00000192 eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00002297 eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00000043 eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00000000 eol_documents_ascii_nonHTML.txt 346289845 346289853 mud flats ENVO:00000012 eol_documents_ascii_nonHTML.txt 346289871 346289873 mud ENVO:01000001 eol_documents_ascii_nonHTML.txt 346289871 346289873 mud ENVO:00010483 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000180 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000191 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00002297 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000176 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000000 eol_documents_ascii_nonHTML.txt 346289905 346289910 mounds ENVO:00000477 Traversing all IS_A, PART_OF Relationships in EnvO Tags corresponding to “Habitat” text data object: http://eol.org/data_objects/31415353 of EOL Taxon Phoenicopterus ruber (Greater Flamingo): http://eol.org/pages/913221 TDWG – 27 th Oct 2014 – Jönköping
Monthly Updates In collab.: Dr. Jennifer Hammock, Mr. Patrick Leary, Dr. Katja Schulz, Dr. Cyndy Parr TDWG – 27 th Oct 2014 – Jönköping
Recommend
More recommend
