Abstract
In this chapter, we enable machine reading comprehension (MRC) with linguistic knowledge to improve answering long, complex questions. The traditional MRC is integrated with information retrieval-based candidate answer selection component which ranks answers relying on syntactic and semantic generalization. We also explore an MRC answer-correction scenario where the resulting MRC answer is evaluated by generalization and updated if necessary. We observe a performance boost of 7%–10% by enabling MRC with syntactic, semantic, and discourse features depending on the question complexity; the greater the question complexity, the stronger the boost.
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 callMore From: Artificial Intelligence for Healthcare Applications and Management
Disclaimer: 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.
