A Study on Abstract Meaning Representation Applications
عنوان مقاله: A Study on Abstract Meaning Representation Applications
شناسه ملی مقاله: AISC01_055
منتشر شده در اولین کنفرانس هوش مصنوعی و پردازش هوشمند در سال 1401
شناسه ملی مقاله: AISC01_055
منتشر شده در اولین کنفرانس هوش مصنوعی و پردازش هوشمند در سال 1401
مشخصات نویسندگان مقاله:
Nasim Tohidi - K. N. Toosi University of Technology, Artificial Intelligence Department, Faculty of Computer Engineering Tehran,Iran
Chitra Dadkhah - K. N. Toosi University of Technology, Artificial Intelligence Department, Faculty of Computer Engineering Tehran,Iran
خلاصه مقاله:
Nasim Tohidi - K. N. Toosi University of Technology, Artificial Intelligence Department, Faculty of Computer Engineering Tehran,Iran
Chitra Dadkhah - K. N. Toosi University of Technology, Artificial Intelligence Department, Faculty of Computer Engineering Tehran,Iran
Abstract Meaning Representation (AMR) is a representation model in which AMRs arerooted and labeled graphs that capture semantics on sentence-level and abstract away fromMorpho-Syntactic properties. The graph’s nodes represent meaning concepts, and the edge labelsshow relations between them. AMR application in Natural Language Processing tasks is widelyincreasing as a principal form of structured sentence semantics, and it is considered as a turningpoint for NLP research. In this paper, we studied the recent works on AMR applications in variousNLP tasks, which mostly worked on English language. Moreover, we compare them and discusssome basic features of them.
کلمات کلیدی: Abstract Meaning Representation, Application, Natural Language Processing, Text, Semantic
صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/1549619/