Analyzing the Effect of Multi-task Learning for Biomedical Named Entity Recognition

Akdemir, Arda; Shibuya, Tetsuo

doi:10.48550/arxiv.2011.00425

Cited by 1 publication

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NER in biology domains has additional challenges due to the pace of new named entities being added, lack of naming convention, lengthy names, presence of special characters, and frequent and variable use of abbreviations. 5,6 Figure 1 shows an example sentence containing chemicals, species, and cell line entities.…”

Section: ■ Background and Related Workmentioning

confidence: 99%

“…As the number of desired entity classes grows, the task of performing inference becomes more time-and resource-consuming. Recent work in multitask learning helps mitigates this issue by sharing the transformer encoder layer between all NER tasks, 5 which makes the problem scalable. Another possible byproduct of this approach is shared information learned in the encoder layer that may improve the performance on a task compared to a single task model.…”

Section: ■ Conclusion and Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Discovering Content through Text Mining for a Synthetic Biology Knowledge System

et al. 2022

View full text Add to dashboard Cite

Scientific articles contain a wealth of information about experimental methods and results describing biological designs. Due to its unstructured nature and multiple sources of ambiguity and variability, extracting this information from text is a difficult task. In this paper, we describe the development of the synthetic biology knowledge system (SBKS) text processing pipeline. The pipeline uses natural language processing techniques to extract and correlate information from the literature for synthetic biology researchers. Specifically, we apply named entity recognition, relation extraction, concept grounding, and topic modeling to extract information from published literature to link articles to elements within our knowledge system. Our results show the efficacy of each of the components on synthetic biology literature and provide future directions for further advancement of the pipeline.

show abstract

Section: ■ Background and Related Workmentioning

confidence: 99%

Section: ■ Conclusion and Future Workmentioning

confidence: 99%