Deep Learning for Natural Language Processing (DLNLP)

I. Objectives

Natural Language Processing (NLP)—a research domain primarily focused on text analysis to enable computers to understand human language—has made significant advancements in recent years. These developments have revolutionized various areas and transformed how we communicate and interact with machines by enhancing their ability to comprehend human languages and dialects. However, many challenges remain to be addressed or improved to enhance user performance and experience further. This Special Issue aims to provide a comprehensive overview of current trends, emerging technologies, and challenges in NLP.

The primary objective of this Special Issue is to present innovative approaches from the research community. It aims to gather the latest advancements in deep learning, focusing on its applications in NLP. The goal is to present novel ideas and potential outcomes, encompassing theoretical perspectives, methodological contributions (including recently developed methods), and practical implementations.

Additionally, this Special Issue encourages comparative analyses of deep learning models in NLP. Such comparisons involve critically evaluating these models’ efficiency and accuracy across diverse datasets and real-world scenarios. The aim is to offer valuable insights into the generalizability and interpretability of these models, thereby driving advancements in their practical applicability.

II. Scope

We propose a special session that will cover topics including, but not limited to, the following:

• Corpus Construction and Benchmarking for NLP
• Deep Learning for Natural Language Understanding and Generation
• Neural Machine Translation and Low-Resource NLP
• Sentiment, Emotion, and Social Media Analysis
• Conversational NLP and Dialogue Systems
• Large Language Models and Foundation Models
• Efficient Fine-Tuning and Adaptation of LLMs
• Retrieval-Augmented Generation and Knowledge-Enhanced NLP
• LLM-based Agents, Reasoning, and Planning
• Multilingual and Cross-Lingual NLP
• Multimodal Natural Language Processing
• Multimodal Large Language and Vision-Language Models
• Visual Question Answering and Multimodal Question Answering
• Document, Chart, and Table Question Answering
• Multimodal Sentiment and Emotion Analysis
• Speech-Language and Audio-Language Processing
• Text, Image, Video, and Multimodal Generation
• Synthetic Data Generation and Data Augmentation for NLP
• Hallucination, Bias, Robustness, and Trustworthy NLP
• Evaluation and Benchmarking of NLP, LLM, and Multimodal Systems
• Efficient and On-Device NLP/LLM
• Applications of Deep Learning and LLMs in Real-World NLP
• etc.

III. Submission link: click here 

Please select the Track/Session: “Deep Learning for Natural Language Processing (DLNLP)” during submission

IV. Session Organizers

• Le Anh Cuong, Ton Duc Thang University, Ho Chi Minh City, Vietnam. Email: leanhcuong@tdtu.edu.vn
• Joy Wang, Queensland University of Technology, Brisbane, Australia Email: y355.wang@connect.qut.edu.au 
• Tran Thanh Phuoc, Ton Duc Thang University, Ho Chi Minh City, Vietnam. Email: tranthanhphuoc@tdtu.edu.vn
• Nguyen Hong Buu Long, VNU-HCMC University of Science, Ho Chi Minh City, Vietnam. Email: nhblong@fit.hcmus.edu.vn