Improving accessibility and distinction between negative results in biomedical relation extraction
Accessible negative results are relevant for researchers and clinicians not only to limit their search space but also to prevent the costly re-exploration of research hypotheses. However, most biomedical relation extraction datasets do not seek to distinguish between a false and a negative relation...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BioMed Central
2020-06-01
|
| Series: | Genomics & Informatics |
| Subjects: | |
| Online Access: | http://genominfo.org/upload/pdf/gi-2020-18-2-e20.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572860186492928 |
|---|---|
| author | Diana Sousa Andre Lamurias Francisco M. Couto |
| author_facet | Diana Sousa Andre Lamurias Francisco M. Couto |
| author_sort | Diana Sousa |
| collection | DOAJ |
| description | Accessible negative results are relevant for researchers and clinicians not only to limit their search space but also to prevent the costly re-exploration of research hypotheses. However, most biomedical relation extraction datasets do not seek to distinguish between a false and a negative relation among two biomedical entities. Furthermore, datasets created using distant supervision techniques also have some false negative relations that constitute undocumented/unknown relations (missing from a knowledge base). We propose to improve the distinction between these concepts, by revising a subset of the relations marked as false on the phenotype-gene relations corpus and give the first steps to automatically distinguish between the false (F), negative (N), and unknown (U) results. Our work resulted in a sample of 127 manually annotated FNU relations and a weighted-F1 of 0.5609 for their automatic distinction. This work was developed during the 6th Biomedical Linked Annotation Hackathon (BLAH6). |
| format | Article |
| id | doaj-art-1aad482b39284cf8a6047b5d67c9cdcd |
| institution | Kabale University |
| issn | 2234-0742 |
| language | English |
| publishDate | 2020-06-01 |
| publisher | BioMed Central |
| record_format | Article |
| series | Genomics & Informatics |
| spelling | doaj-art-1aad482b39284cf8a6047b5d67c9cdcd2025-02-02T06:27:18ZengBioMed CentralGenomics & Informatics2234-07422020-06-01182e2010.5808/GI.2020.18.2.e20606Improving accessibility and distinction between negative results in biomedical relation extractionDiana SousaAndre LamuriasFrancisco M. CoutoAccessible negative results are relevant for researchers and clinicians not only to limit their search space but also to prevent the costly re-exploration of research hypotheses. However, most biomedical relation extraction datasets do not seek to distinguish between a false and a negative relation among two biomedical entities. Furthermore, datasets created using distant supervision techniques also have some false negative relations that constitute undocumented/unknown relations (missing from a knowledge base). We propose to improve the distinction between these concepts, by revising a subset of the relations marked as false on the phenotype-gene relations corpus and give the first steps to automatically distinguish between the false (F), negative (N), and unknown (U) results. Our work resulted in a sample of 127 manually annotated FNU relations and a weighted-F1 of 0.5609 for their automatic distinction. This work was developed during the 6th Biomedical Linked Annotation Hackathon (BLAH6).http://genominfo.org/upload/pdf/gi-2020-18-2-e20.pdfbiomedical researchknowledge basenegative resultsrelation extraction |
| spellingShingle | Diana Sousa Andre Lamurias Francisco M. Couto Improving accessibility and distinction between negative results in biomedical relation extraction Genomics & Informatics biomedical research knowledge base negative results relation extraction |
| title | Improving accessibility and distinction between negative results in biomedical relation extraction |
| title_full | Improving accessibility and distinction between negative results in biomedical relation extraction |
| title_fullStr | Improving accessibility and distinction between negative results in biomedical relation extraction |
| title_full_unstemmed | Improving accessibility and distinction between negative results in biomedical relation extraction |
| title_short | Improving accessibility and distinction between negative results in biomedical relation extraction |
| title_sort | improving accessibility and distinction between negative results in biomedical relation extraction |
| topic | biomedical research knowledge base negative results relation extraction |
| url | http://genominfo.org/upload/pdf/gi-2020-18-2-e20.pdf |
| work_keys_str_mv | AT dianasousa improvingaccessibilityanddistinctionbetweennegativeresultsinbiomedicalrelationextraction AT andrelamurias improvingaccessibilityanddistinctionbetweennegativeresultsinbiomedicalrelationextraction AT franciscomcouto improvingaccessibilityanddistinctionbetweennegativeresultsinbiomedicalrelationextraction |