A SURVEY ON MULTI-HOP READING COMPREHENSION

A SURVEY ON MULTI-HOP READING COMPREHENSION
Author(s):
AFREEN SULTANA
Keywords:
Multi-hop Reading Comprehension (MHRC), WikiHop, HotpotQA
Abstract
Multi-hop Reading Comprehension (MHRC) is a dynamic field of Natural Language Processing (NLP) with real-world applications. The great advancement in this field in recent years has been largely due to the emergence of large databases and in-depth learning. At present, many MHRC models have already surpassed human performance in limited data sets despite the huge gap between existing MHRC models and a real understanding of human-level learning. This highlights the need to improve existing data sets, analytical metrics, and models in order to move current MHRC models to a “real” understanding. To address the current lack of comprehensive survey of existing MRC activities, analytical metrics, and data sets, here, (1) we analyzed MHRC activities and data sets (2) summarized eight different but effective strategies for learning comprehension.
Article Details
Unique Paper ID: 156962 Publication Volume & Issue: Volume 9, Issue 5 Page(s): 873 - 878
Article Preview & Download

Share This Article

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org