English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The purpose of this project is to evaluate three language models named BERT,ALBERT, and LongFormer on the Question Answering dataset called DuoRC. Thelanguage model task has two inputs, a question, and a context. The context is aparagraph or an entire document while the output is the answer based on thecontext. The goal is to perform grid search hyperparameter fine-tuning usingDuoRC. Pretrained weights of the models are taken from the Huggingface library.Different sets of hyperparameters are used to fine-tune the models using twoversions of DuoRC which are the SelfRC and the ParaphraseRC. The results showthat the ALBERT (pretrained using the SQuAD1 dataset) has an F1 score of 76.4and an accuracy score of 68.52 after fine-tuning on the SelfRC dataset. TheLongformer model (pretrained using the SQuAD and SelfRC datasets) has an F1score of 52.58 and an accuracy score of 46.60 after fine-tuning on theParaphraseRC dataset. The current results outperformed the results from theprevious model by DuoRC.

Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC