Linguistically Informed Relation Extraction and Neural Architectures for Nested Named Entity Recognition in BioNLP-OST 2019

TL;DR

This paper presents a linguistically informed approach to nested Named Entity Recognition and Relation Extraction in biomedical texts, achieving top performance in BioNLP Shared Tasks 2019 across multiple languages and tasks.

Contribution

The authors introduce a novel, linguistically informed method for nested NER and RE, incorporating hybrid loss, multi-task learning, and ensembling, with demonstrated effectiveness in English and Spanish biomedical literature.

Findings

Ranked first in BB-2019 norm+NER task with SER of 0.7159

Achieved F1-score of 0.8662 on PharmaCo NER task

Ranked first in SeeDev-binary Relation Extraction with F1-score of 0.3738

Abstract

Named Entity Recognition (NER) and Relation Extraction (RE) are essential tools in distilling knowledge from biomedical literature. This paper presents our findings from participating in BioNLP Shared Tasks 2019. We addressed Named Entity Recognition including nested entities extraction, Entity Normalization and Relation Extraction. Our proposed approach of Named Entities can be generalized to different languages and we have shown it's effectiveness for English and Spanish text. We investigated linguistic features, hybrid loss including ranking and Conditional Random Fields (CRF), multi-task objective and token-level ensembling strategy to improve NER. We employed dictionary based fuzzy and semantic search to perform Entity Normalization. Finally, our RE system employed Support Vector Machine (SVM) with linguistic features. Our NER submission (team:MIC-CIS) ranked first in BB-2019 norm+NER task with standard error rate (SER) of 0.7159 and showed competitive performance on PharmaCo NER task with F1-score of 0.8662. Our RE system ranked first in the SeeDev-binary Relation Extraction Task with F1-score of 0.3738.