Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs

Sharma, Soumya; Santra, Bishal; Jana, Abhik; Tokala, Santosh; Ganguly, Niloy; Goyal, Pawan

doi:10.18653/v1/d19-1631

Cited by 23 publications

(12 citation statements)

References 20 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments reported in Section 4 show that our proposed method can improve the performance of each of these biomedical BERT models, demonstrating the importance of disease knowledge infusion. Biomedical Knowledge Integration Methods with UMLS: Previous non-BERT methods connect data of downstream tasks with knowledge bases like UMLS (Sharma et al, 2019;Romanov and Shivade, 2018). For example, they map medical concepts and semantic relationships in the data to UMLS.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition

He¹,

Zhu²,

Zhang³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Knowledge of a disease includes information of various aspects of the disease, such as signs and symptoms, diagnosis and treatment. This disease knowledge is critical for many healthrelated and biomedical tasks, including consumer health question answering, medical language inference and disease name recognition. While pre-trained language models like BERT have shown success in capturing syntactic, semantic, and world knowledge from text, we find they can be further complemented by specific information like knowledge of symptoms, diagnoses, treatments, and other disease aspects. Hence, we integrate BERT with disease knowledge for improving these important tasks. Specifically, we propose a new disease knowledge infusion training procedure and evaluate it on a suite of BERT models including BERT, BioBERT, SciBERT, Clinical-BERT, BlueBERT, and ALBERT. Experiments over the three tasks show that these models can be enhanced in nearly all cases, demonstrating the viability of disease knowledge infusion. For example, accuracy of BioBERT on consumer health question answering is improved from 68.29% to 72.09%, while new SOTA results are observed in two datasets. We make our data and code freely available.

show abstract

Section: Related Workmentioning

confidence: 99%

“…For example, they map medical concepts and semantic relationships in the data to UMLS. After that, these concepts and relationships are encoded into embeddings and incorporated into models (Sharma et al, 2019). The advantage is that they can explicitly incorporate knowledge into models.…”

Section: Related Workmentioning

confidence: 99%

Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition

He¹,

Zhu²,

Zhang³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Further development of this approach will enable ongoing analysis and deep searching of large collections of literature, such as PubMed, and application to other disease areas, as well as for target or biomarker discovery. [19][20][21] Contributors TH, GC, TS, SK and YB conceived the study and performed the data analysis and tool development. All authors contributed to the manuscript preparation and writing and critically improved the manuscript.…”

Section: Discussionmentioning

confidence: 99%

Network graph representation of COVID-19 scientific publications to aid knowledge discovery

Cernile

Heritage

Sebire

et al. 2021

BMJ Health Care Inform

View full text Add to dashboard Cite

IntroductionNumerous scientific journal articles related to COVID-19 have been rapidly published, making navigation and understanding of relationships difficult.MethodsA graph network was constructed from the publicly available COVID-19 Open Research Dataset (CORD-19) of COVID-19-related publications using an engine leveraging medical knowledge bases to identify discrete medical concepts and an open-source tool (Gephi) to visualise the network.ResultsThe network shows connections between diseases, medications and procedures identified from the title and abstract of 195 958 COVID-19-related publications (CORD-19 Dataset). Connections between terms with few publications, those unconnected to the main network and those irrelevant were not displayed. Nodes were coloured by knowledge base and the size of the node related to the number of publications containing the term. The data set and visualisations were made publicly accessible via a webtool.ConclusionKnowledge management approaches (text mining and graph networks) can effectively allow rapid navigation and exploration of entity inter-relationships to improve understanding of diseases such as COVID-19.

show abstract

Section: Discussionmentioning

confidence: 99%

Network Graph Representation of COVID-19 Scientific Publications to Aid Knowledge Discovery

Cernile

Sebire

Gordon

et al. 2020

Preprint

View full text Add to dashboard Cite

Introduction: Numerous scientific journal articles have been rapidly published related to COVID-19 making navigation and understanding of relationships difficult. Methods: A graph network was constructed from the publicly available CORD-19 database of COVID-19-related publications using an engine leveraging medical knowledgebases to identify discrete medical concepts and an open source tool (Gephi) used to visualise the network. Results: The network shows connections between disease, medication and procedures identified from title and abstracts of 195,958 COVID-19 related publications (CORD-19 Dataset). Connections between terms with few publications, those unconnected to the main network and those irrelevant were not displayed. Nodes were coloured by knowledgebase and node size related to the number of publications containing the term. The dataset and visualisations made publicly accessible via a webtool. Conclusion: Knowledge management approaches (text mining and graph networks) can effectively allow rapid navigation and exploration of entity interrelationships to improve understanding of diseases such as COVID-19.

show abstract

Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs

Cited by 23 publications

References 20 publications

Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition

Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition

Network graph representation of COVID-19 scientific publications to aid knowledge discovery

Network Graph Representation of COVID-19 Scientific Publications to Aid Knowledge Discovery

Contact Info

Product

Resources

About