Spell Checker for Consumer Language (CSpell)
This on-demand webinar does not offer CE credit.
Lead author Chris J. Lu will discuss this month's JAMIA Journal Club selection:
Lu CJ, Aronson AR, Shooshan SE, Demner-Fushman D. Spell checker for consumer language (CSpell). J Am Med Inform Assoc. 2019 Mar 1;26(3):211-218. doi: 10.1093/jamia/ocy171.
Watch the Recording
Presenter
Chris J. Lu, PhD
Managers/Moderators
Kelson Zawack, PhD
Tiffany J. Callahan, MPH, PhD Candidate
Statement of Purpose
Automated understanding of consumer health inquiries might be hindered by misspellings. To detect and correct various types of spelling errors in consumer health questions, we developed a distributable spell-checking tool, CSpell, that handles nonword errors, real-word errors, word boundary infractions, punctuation errors, and combinations of the above.
We developed a novel approach of using dual embedding within Word2vec for context-dependent corrections. This technique was used in combination with dictionary-based corrections in a 2-stage ranking system. We also developed various splitters and handlers to correct word boundary infractions. All correction approaches are integrated to handle errors in consumer health questions.
CSpell improves over the state of the art and provides near real-time automatic misspelling detection and correction in consumer health questions to achieve an F1 score of 80.93% and 69.17% for spelling error detection and correction, respectively.
Target Audience
The target audience for this activity is professionals and students interested in biomedical and health informatics.
Learning Objectives
The general learning objective for all of the JAMIA Journal Club webinars is that participants will
- Use a critical appraisal process to assess article validity and to gauge article findings' relevance to practice
After this live activity, the participant should be better able to:
- Understand different types of spell errors and corrections in consumer’s questions
- Understand features of CSpell
- Better use and configure CSpell for NLP projects
Commercial Support
No commercial support was received for this activity.
Disclosure Policy
As a provider accredited by the ACCME, AMIA requires that everyone who is in a position to control the content of an educational activity disclose all relevant financial relationships with any commercial interest for 12 months prior to the educational activity.
The ACCME considers relationships of the person involved in the CME activity to include financial relationships of a spouse or partner.
Faculty and planners who refuse to disclose relevant financial relationships will be disqualified from participating in the CME activity. For an individual with no relevant financial relationship(s), the participants must be informed that no conflicts of interest or financial relationship(s) exist.
AMIA uses a number of methods to resolve potential conflicts of interest, including: limiting content of the presentation to that which has been reviewed by one or more peer reviewers; ensuring that all scientific research referred to conforms to generally accepted standards of experimental design, data collection, and analysis; undertaking review of the educational activity by a content reviewer to evaluate for potential bias, balance in presentation, evidence-based content or other indicators of integrity, and absence of bias; monitoring the educational activity to evaluate for commercial bias in the presentation; and/or reviewing participant feedback to evaluate for commercial bias in the activity.
Disclosures for this Activity
These faculty, planners, and staff who are in a position to control the content of this activity disclose that they and their life partners have no relevant financial relationships with commercial interests:
JAMIA Journal Club Faculty: Chris J. Lu
JAMIA Journal Club planners: Michael Chiang, Kelson Zawack, Tiffany J. Callahan
AMIA staff: Susanne Arnold, Pesha Rubinstein