NLP based Model for Classification of Complaints: Autonomous and Intelligent System

Quratulain, -; Shaukat, Arslan; Saif, Usman

doi:10.1109/icodt255437.2022.9787456

Cited by 1 publication

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Filgueiras et al (2019) combined both traditional and deep learning methods for analyzing complaints associated with a Portuguese government institution [68]. Meanwhile, Shaukat et al (2022) adopted classical NLP approaches to classify citizen feedback sourced from a government portal [69]. Highlighting NLP's versatility in public feedback integration, Kowalski et al (2020) applied topic modeling to evaluate public input on primary healthcare in England, emphasizing NLP's capacity to integrate citizen viewpoints into government services [46].…”

Section: Natural Language Processing and Public Sectormentioning

confidence: 99%

Augmenting Large Language Models for Enhanced Interaction with Government Data Repositories

Trust,

Omala,

Minghim

2024

Preprint

View full text Add to dashboard Cite

In the modern digital landscape, government agencies globally are shifting services online to enhance transparency and public engagement. However, the vast digital content can be daunting for citizens seeking information. Addressing this, our research evaluates the efficacy of Large Language Models (LLMs), like ChatGPT, in the public sector, highlighting their potential in extracting relevant insights and optimizing information navigation. Our approach integrates non-parametric data from various sources focusing on information posted on three irish websites; the government publications, health services, and the Citizens Information websites, using retrieval-augmented models. Empirical evaluations show that the llama2 model, with $13$ billion parameters, achieves up to 90% for government publication releases and up to 96.12% for health information enhancement when complemented with retrieval augmentation, with other models also showing substantial improvements. These results emphasize the transformative potential of retrieval-augmented frameworks in keeping LLMs updated with the evolving public information domain.

show abstract

Section: Natural Language Processing and Public Sectormentioning

confidence: 99%