%0 Generic %1 dong2023reveal %A Dong, Hang %A Chen, Jiaoyan %A He, Yuan %A Liu, Yinan %A Horrocks, Ian %D 2023 %K BERT-based BLINK KB-enrichment NIL-entities biomedical_texts clinical_nlp clinical_notes entity_linking knowledge-base-enrichment medmentions myown ontologies out-of-KB unknown_entities %T Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking %U http://arxiv.org/abs/2302.07189 %X Discovering entity mentions that are out of a Knowledge Base (KB) from texts plays a critical role in KB maintenance, but has not yet been fully explored. The current methods are mostly limited to the simple threshold-based approach and feature-based classification; the datasets for evaluation are relatively rare. In this work, we propose BLINKout, a new BERT-based Entity Linking (EL) method which can identify mentions that do not have a corresponding KB entity by matching them to a special NIL entity. To this end, we integrate novel techniques including NIL representation, NIL classification, and synonym enhancement. We also propose Ontology Pruning and Versioning strategies to construct out-of-KB mentions from normal, in-KB EL datasets. Results on four datasets of clinical notes and publications show that BLINKout outperforms existing methods to detect out-of-KB mentions for medical ontologies UMLS and SNOMED CT.

@misc{dong2023reveal, abstract = {Discovering entity mentions that are out of a Knowledge Base (KB) from texts plays a critical role in KB maintenance, but has not yet been fully explored. The current methods are mostly limited to the simple threshold-based approach and feature-based classification; the datasets for evaluation are relatively rare. In this work, we propose BLINKout, a new BERT-based Entity Linking (EL) method which can identify mentions that do not have a corresponding KB entity by matching them to a special NIL entity. To this end, we integrate novel techniques including NIL representation, NIL classification, and synonym enhancement. We also propose Ontology Pruning and Versioning strategies to construct out-of-KB mentions from normal, in-KB EL datasets. Results on four datasets of clinical notes and publications show that BLINKout outperforms existing methods to detect out-of-KB mentions for medical ontologies UMLS and SNOMED CT.}, added-at = {2023-02-15T09:57:31.000+0100}, author = {Dong, Hang and Chen, Jiaoyan and He, Yuan and Liu, Yinan and Horrocks, Ian}, biburl = {https://www.bibsonomy.org/bibtex/28d3d22e7789e0920f1a07da7a1f6bb75/hangdong}, description = {[2302.07189] Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking}, interhash = {2d0fe7c2a0caa8bce2f4ff4e2f498b50}, intrahash = {8d3d22e7789e0920f1a07da7a1f6bb75}, keywords = {BERT-based BLINK KB-enrichment NIL-entities biomedical_texts clinical_nlp clinical_notes entity_linking knowledge-base-enrichment medmentions myown ontologies out-of-KB unknown_entities}, note = {cite arxiv:2302.07189}, timestamp = {2023-02-15T09:57:31.000+0100}, title = {Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking}, url = {http://arxiv.org/abs/2302.07189}, year = 2023 }