Abstract
This paper presents a method for decomposing long, complex consumer health questions. Our approach largely decomposes questions using their syntactic structure, recognizing independent questions embedded in clauses, as well as coordinations and exemplifying phrases. Additionally, we identify elements specific to disease-related consumer health questions, such as the focus disease and background information. To achieve this, our approach combines rank-and-filter machine learning methods with rule-based methods. Our results demonstrate significant improvements over the heuristic methods typically employed for question decomposition that rely only on the syntactic parse tree.
Highlights
Natural language questions provide an intuitive method for consumers to query for health-related content
These annotations distinguish between sentences that contain questions and background information. They identify when a question sentence can be split in multiple independent questions, and Proceedings of the 2014 Workshop on Biomedical Natural Language Processing (BioNLP 2014), pages 29–37, Baltimore, Maryland USA, June 26-27 2014. c 2014 Association for Computational Linguistics when they contain optional or coordinated information embedded within a question. For each of these decomposition annotations, we propose a combination of machine learning (ML) and rule based methods
We evaluate each of these methods on a set of 1,467 consumer health questions related to genetic and rare diseases
Summary
Natural language questions provide an intuitive method for consumers (non-experts) to query for health-related content. What cautions or additional treatments are required to manage the disease with a transplanted kidney? The background sentence is necessary to understand the second question: the anaphor this must be resolved to an enzyme treatment, and the predicate continue’s implicit argument that must be re-constructed from the discourse (i.e., continue after a kidney transplant). 2. Will enzyme treatment for Fabry disease need to be continued after a kidney transplant? 4. What additional treatments are required to manage Fabry disease with a transplanted kidney?. Demner-Fushman and Abhyankar (2012) propose a method for extracting frames from queries for the purpose of cohort retrieval Their method assumes syntactic dependencies exist between the necessary frame elements, and is not well-suited to handle long, multi-sentence questions.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
