[HTML][HTML] A survey of GPT-3 family large language models including ChatGPT and GPT-4

KS Kalyan - Natural Language Processing Journal, 2023 - Elsevier
Large language models (LLMs) are a special class of pretrained language models (PLMs)
obtained by scaling model size, pretraining corpus and computation. LLMs, because of their …

[HTML][HTML] Pre-trained language models for keyphrase prediction: A review

U Muhammad, T Sultana, YK Lee - ICT Express, 2024 - Elsevier
Keyphrase Prediction (KP) is essential for identifying keyphrases in a document that can
summarize its content. However, recent Natural Language Processing (NLP) advances have …

Toward human perception-centric video thumbnail generation

T Yang, F Wang, J Lin, Z Qi, Y Wu, J Xu… - Proceedings of the 31st …, 2023 - dl.acm.org
Video thumbnail plays an essential role in summarizing video content into a compact and
concise image for users to browse efficiently. However, automatically generating attractive …

Automated Detection of Social Conflict Drivers in Civil Infrastructure Projects Using Natural Language Processing

S Baek, D Namgoong, J Won, SH Han - Applied Sciences, 2023 - mdpi.com
Early detection and mitigation of social conflict in civil infrastructure projects is essential due
to its significant impact on project performance and social governance. Nevertheless, there …

[HTML][HTML] Innovative agricultural ontology construction using NLP methodologies and graph neural network

KS Saravanan, V Bhagavathiappan - Engineering Science and Technology …, 2024 - Elsevier
Advancements in technology brought various innovations to agricultural practices. As a part
of the development, establishing an agricultural ontology would unleash the growth of cross …

Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shuffling

B Chen, M Iwaihara - Pacific Rim International Conference on Artificial …, 2023 - Springer
Keyphrase generation is a task of identifying a set of phrases that best represent the main
topics or themes of a given text. Keyphrases are dividend int present and absent …

Theme-driven Keyphrase Extraction to Analyze Social Media Discourse

W Romano, O Sharif, M Basak, J Gatto… - Proceedings of the …, 2024 - ojs.aaai.org
Social media platforms are vital resources for sharing self-reported health experiences,
offering rich data on various health topics. Despite advancements in Natural Language …

Capturing the Concept Projection in Metaphorical Memes for Downstream Learning Tasks

S Acharya, B Das, TSB Sudarshan - IEEE Access, 2023 - ieeexplore.ieee.org
Metaphorical memes, where a source concept is projected into a target concept, are an
essential construct in figurative language. In this article, we present a novel approach for …

Improving Absent Keyphrase Generation with Diversity Heads

E Thomas, S Vajjala - Findings of the Association for …, 2024 - aclanthology.org
Keyphrase Generation (KPG) is the task of automatically generating appropriate keyphrases
for a given text, with a wide range of real-world applications such as document indexing and …

[PDF][PDF] Enhancing Relational Triple Extraction in Specific Domains: Semantic Enhancement and Synergy of Large Language Models and Small Pre-Trained Language …

J Li, J Hu, G Zhang - Computers, Materials & Continua, 2024 - cdn.techscience.cn
In the process of constructing domain-specific knowledge graphs, the task of relational triple
extraction plays a critical role in transforming unstructured text into structured information …