Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management 2021
DOI: 10.1145/3459637.3482128
|View full text |Cite
|
Sign up to set email alerts
|

Knowledge-Aware Neural Networks for Medical Forum Question Classification

Abstract: Online medical forums have become a predominant platform for answering health-related information needs of consumers. However, with a significant rise in the number of queries and the limited availability of experts, it is necessary to automatically classify medical queries based on a consumer's intention, so that these questions may be directed to the right set of medical experts. Here, we develop a novel medical knowledge-aware BERT-based model (M BERT) that explicitly gives more weightage to medical concept… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 23 publications
0
3
0
Order By: Relevance
“…The Medical Forum Question Classification project aims to assist medical professionals with health-related questions, using the Med BERT model. BERT fine-tuning techniques are examined for text classification, achieving state-of-the-art results on multiple datasets [31][32][33][34]. ATICM combines syntactic and semantic analysis for question classification, using WordNet-based hypernym expansion.…”
Section: Literature Reviewmentioning
confidence: 99%
“…The Medical Forum Question Classification project aims to assist medical professionals with health-related questions, using the Med BERT model. BERT fine-tuning techniques are examined for text classification, achieving state-of-the-art results on multiple datasets [31][32][33][34]. ATICM combines syntactic and semantic analysis for question classification, using WordNet-based hypernym expansion.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Knowledge-aware models in medical applications are expected to lead to more efficient and accurate medical services. MedBERT [167] is a BERT-based model for automatic classification of medical queries, which incorporates medical domain knowledge as side information in the model, and finally, BERT encoding to complete the classification task of medical problems. In terms of disease-assisted detection, the knowledge graph can be used to assist in determining information such as physical examinations and test results.…”
Section: Domain-specific Applicationsmentioning
confidence: 99%
“…Medical forum platforms provide a valuable resource for patients, caregivers, and medical professionals to seek and exchange health information. Efficiently classifying questions asked on these platforms is essential for organizing the content and providing relevant and accurate responses [4]. Question classification (QC) aims to assign predefined labels or categories to input questions, enabling effective information retrieval and facilitating knowledge sharing [5].…”
Section: Introductionmentioning
confidence: 99%