You are here

Consumer Health Question Answering

Project information

The consumer health question answering project was launched to support NLM customer services that receive about 90,000 requests a year from a world-wide pool of customers. The requests are categorized by the customer support services staff and are either answered using about 300 stock answers (with or without modifications) or researched and answered by the staff manually. Responding to a customer with a stock reply takes approximately 4 minutes; answering with a personalized stock reply takes about 10 minutes. To reduce the time and cost of customer services, NLM launched the Consumer Health Information and Question Answering (CHIQA) project.  The CHIQA project conducts research in both the automatic classification of customers’ requests and the automatic answering of consumer health questions.

The analysis of the requests identified subsets of reference questions that could be answered automatically.  LHC researchers have developed a customer service support system that categorizes the incoming requests and prepares answers for review by staff responding to customer requests.  The system combines sophisticated statistical methods with knowledge-based natural language processing techniques.  The pilot system was integrated in customer services workflow in May 2014. As the system matures, it could immediately provide answers to customers while they are visiting NLM Web pages.


Question Decomposition Data

Question Type Data

CHQA Named Entity Dataset

Consumer Health Spelling Error Dataset

Ben Abacha A, Agichtein E, Pinter Y, Demner-Fushman D. Overview of the Medical QA Task @ TREC 2017 LiveQA Track. TREC, Gaithersburg, MD, 2017.
Kilicoglu H, Ben Abacha A, Mrabet Y, Shooshan SE, Rodriguez L, Masterton K, Demner-Fushman D. Semantic annotation of consumer health questions. BMC Bioinformatics. 2018 Feb 6;19(1):34. doi: 10.1186/s12859-018-2045-1.
Deardorff A, Masterton K, Roberts K, Kilicoglu H, Demner-Fushman D. A protocol-driven approach to automatically finding authoritative answers to consumer health questions in online resources. JASIST, 68(7): 1724-1736. doi: 10.1002/asi.23806.
Ben Abacha A, Demner-Fushman D. NLM_NIH at SemEval-2017 Task 3: from Question Entailment to Question Similarity for Community Question Answering. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval@ACL) 2017: 349-352.
Mrabet Y, Kilicoglu H, Roberts K, Demner-Fushman D. Combining Open-domain and Biomedical Knowledge for Topic Recognition in Consumer Health Questions. AMIA 2016 Annual Symposium, Chicago, IL, November 12-16, 2016.
Demner-Fushman D, Elhadad N. Aspiring to Unintended Consequences of Natural Language Processing: A Review of Recent Developments in Clinical and Consumer-Generated Text Processing. IMIA Yearbook of Medical Informatics 2016.
Mrabet Y, Kilicoglu H, Demner-Fushman D. Unsupervised Ranking of Knowledge Bases for Named Entity Recognition. ECAI 2016, The Hague, The Netherlands, 1248-1255.
Roberts K, Demner-Fushman D. Interactive use of online health resources: a comparison of consumer and professional questions. J Am Med Inform Assoc. 2016 Jul;23(4):802-11. doi: 10.1093/jamia/ocw024. Epub 2016 May 4.
Kilicoglu H, Ben Abacha A, Mrabet Y, Roberts K, Rodriguez L, Shooshan SE, Demner-Fushman D. Annotating named entities in consumer health questions. LREC,23-28 May 2016, Portorož.
Demner-Fushman D, Kilicoglu H. Dataset: CHQA Named Entity Dataset