Internet Service Domain
The internet service domain encompasses a broad range of research focused on improving the efficiency and effectiveness of online services. Current research emphasizes adapting models to specific domains, often using techniques like domain adaptation, knowledge distillation, and domain decomposition, frequently incorporating architectures such as U-Nets, transformers, and BERT variants. These advancements aim to enhance performance in tasks like question answering, image segmentation, and speech recognition, while also addressing challenges such as data imbalance, domain shifts, and adversarial attacks. Ultimately, this research strives to create more robust, efficient, and reliable online services across diverse applications.
Papers
On Creating an English-Thai Code-switched Machine Translation in Medical Domain
Parinthapat Pengpun, Krittamate Tiankanon, Amrest Chinkamol, Jiramet Kinchagawat, Pitchaya Chairuengjitjaras, Pasit Supholkhan, Pubordee Aussavavirojekul, Chiraphat Boonnag, Kanyakorn Veerakanjana, Hirunkul Phimsiri, Boonthicha Sae-jia, Nattawach Sataudom, Piyalitt Ittichaiwong, Peerat Limkonchotiwat
Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
Xilin He, Jingyu Hu, Qinliang Lin, Cheng Luo, Weicheng Xie, Siyang Song, Muhammad Haris Khan, Linlin Shen
DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization
Haohan Yuan, Haopeng Zhang