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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Significant advances have been made in recent years on Natural LanguageProcessing with machines surpassing human performance in many tasks, includingbut not limited to Question Answering. The majority of deep learning methodsfor Question Answering targets domains with large datasets and highly maturedliterature. The area of Nuclear and Atomic energy has largely remainedunexplored in exploiting non-annotated data for driving industry viableapplications. Due to lack of dataset, a new dataset was created from the 7000research papers on nuclear domain. This paper contributes to research inunderstanding nuclear domain knowledge which is then evaluated on NuclearQuestion Answering Dataset (NQuAD) created by nuclear domain experts as part ofthis research. NQuAD contains 612 questions developed on 181 paragraphsrandomly selected from the IGCAR research paper corpus. In this paper, theNuclear Bidirectional Encoder Representational Transformers (NukeBERT) isproposed, which incorporates a novel technique for building BERT vocabulary tomake it suitable for tasks with less training data. The experiments evaluatedon NQuAD revealed that NukeBERT was able to outperform BERT significantly, thusvalidating the adopted methodology. Training NukeBERT is computationallyexpensive and hence we will be open-sourcing the NukeBERT pretrained weightsand NQuAD for fostering further research work in the nuclear domain.

NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain