Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Named Entity Recognition from Biomedical Text
As vast amounts of unstructured data are becoming available digitally, computer-based methods to extract relevant and meaningful information are needed. Named entity recognition (NER) is the task of identifying text spans that mention named entities, and to classify them into predefined categories....
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2023
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613421942341632 |
|---|---|
| access_status_str | Open Access |
| author | Guirguis, Maged |
| author_browse | Guirguis, Maged |
| author_facet | Guirguis, Maged |
| author_sort | Guirguis, Maged |
| collection | Thesis |
| description | As vast amounts of unstructured data are becoming available digitally, computer-based methods to extract relevant and meaningful information are needed. Named entity recognition (NER) is the task of identifying text spans that mention named entities, and to classify them into predefined categories. Despite the existence of numerous and well-versed NER methods, the bio-medical domain remains under-studied. The objective of this research is to identify an efficient technique for NER tasks from biomedical data. This is achieved by investigating using deep learning technologies namely pre-trained BERT [1] model and its variances SciBERT [2] and BioBERT [3]. Preprocessing the data before passing it for training influences model performance. There is also investigation with some preprocessing rules to monitor their effect on model performance. Our model outperforms vanilla BERT, and BioBERT where is Precision: 66.20%, Recall: 98.96%, F1: 79.33%. |
| format | Thesis |
| id | oai:fount.aucegypt.edu:etds-3014 |
| institution | American University in Cairo (Egypt) |
| last_indexed | 2026-06-10T12:35:53.165Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from AUC Knowledge Fountain — bepress |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | AUC Knowledge Fountain |
| publisherStr | AUC Knowledge Fountain |
| record_format | dspace |
| source_str | AUC Knowledge Fountain — bepress |
| spelling | oai:fount.aucegypt.edu:etds-3014 Named Entity Recognition from Biomedical Text Guirguis, Maged As vast amounts of unstructured data are becoming available digitally, computer-based methods to extract relevant and meaningful information are needed. Named entity recognition (NER) is the task of identifying text spans that mention named entities, and to classify them into predefined categories. Despite the existence of numerous and well-versed NER methods, the bio-medical domain remains under-studied. The objective of this research is to identify an efficient technique for NER tasks from biomedical data. This is achieved by investigating using deep learning technologies namely pre-trained BERT [1] model and its variances SciBERT [2] and BioBERT [3]. Preprocessing the data before passing it for training influences model performance. There is also investigation with some preprocessing rules to monitor their effect on model performance. Our model outperforms vanilla BERT, and BioBERT where is Precision: 66.20%, Recall: 98.96%, F1: 79.33%. 2023-02-15T08:00:00Z thesis application/pdf https://fount.aucegypt.edu/etds/1983 https://fount.aucegypt.edu/context/etds/article/3014/viewcontent/Maged_Guirguis_Thesis.pdf Theses and Dissertations AUC Knowledge Fountain Keywords: NER; named entity recognition; chemprot; drugprot; BERT; SciBERT; BioBERT Data Science |
| spellingShingle | Keywords: NER; named entity recognition; chemprot; drugprot; BERT; SciBERT; BioBERT Data Science Guirguis, Maged Named Entity Recognition from Biomedical Text |
| title | Named Entity Recognition from Biomedical Text |
| title_full | Named Entity Recognition from Biomedical Text |
| title_fullStr | Named Entity Recognition from Biomedical Text |
| title_full_unstemmed | Named Entity Recognition from Biomedical Text |
| title_short | Named Entity Recognition from Biomedical Text |
| title_sort | named entity recognition from biomedical text |
| topic | Keywords: NER; named entity recognition; chemprot; drugprot; BERT; SciBERT; BioBERT Data Science |
| url | https://fount.aucegypt.edu/etds/1983 https://fount.aucegypt.edu/context/etds/article/3014/viewcontent/Maged_Guirguis_Thesis.pdf |
| work_keys_str_mv | AT guirguismaged namedentityrecognitionfrombiomedicaltext |