INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
To evaluate the performance of model, our
primary approach has been to measure
accuracy of model on validation dataset.
Benchmark datasets used to train and
validate NLP models may often
overestimate the performance. These
observations all stem from the fact that a
model may achieve high performance on a
dataset by learning spurious correlations,
also called dataset artifacts. The model is
then expected to fail in settings where these
artifacts are not present, which may include
real-world testbeds of interest. Our aim in
this paper is to evaluate pre-trained QA
model fine-tuned on SQuAD benchmark
dataset and rigorously test it against
challenging dataset; identify different types
of issues in the model; and further define an
approach to improve the model
performance on one of the specified issues.
Keywords:
Cite Article:
"Improve SQuAD fine-tuned ELECTRA model on Adversarial QA", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 2, page no.c623-c628, February-2024, Available :http://www.ijnrd.org/papers/IJNRD2402269.pdf
Downloads:
000118776
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn