Ta Duc Huy

Ta Duc Huy, Nguyen Anh Tu, Tran Hoang Vu et al.

Existing medical text datasets usually take the form of question and answer pairs that support the task of natural language generation, but lacking the composite annotations of the medical terms. In this study, we publish a Vietnamese dataset of medical questions from patients with sentence-level and entity-level annotations for the Intent Classification and Named Entity Recognition tasks. The tag sets for two tasks are in medical domain and can facilitate the development of task-oriented healthcare chatbots with better comprehension of queries from patients. We train baseline models for the two tasks and propose a simple self-supervised training strategy with span-noise modelling that substantially improves the performance. Dataset and code will be published at https://github.com/tadeephuy/ViMQ

Hoang Thi Thu Uyen, Nguyen Anh Tu, Ta Duc Huy

Despite the rise of recent performant methods in Automatic Speech Recognition (ASR), such methods do not ensure proper casing and punctuation for their outputs. This problem has a significant impact on the comprehension of both Natural Language Processing (NLP) algorithms and human to process. Capitalization and punctuation restoration is imperative in pre-processing pipelines for raw textual inputs. For low resource languages like Vietnamese, public datasets for this task are scarce. In this paper, we contribute a public dataset for capitalization and punctuation recovery for Vietnamese; and propose a joint model for both tasks named JointCapPunc. Experimental results on the Vietnamese dataset show the effectiveness of our joint model compare to single model and previous joint learning model. We publicly release our dataset and the implementation of our model at https://github.com/anhtunguyen98/JointCapPunc

Ankit Yadav, Ta Duc Huy, Lingqiao Liu

Large-scale vision language pre-training has recently shown promise for no-reference image-quality assessment (NR-IQA), yet the relative merits of modern Vision Transformer foundations remain poorly understood. In this work, we present the first systematic evaluation of six prominent pretrained backbones, CLIP, SigLIP2, DINOv2, DINOv3, Perception, and ResNet, for the task of No-Reference Image Quality Assessment (NR-IQA), each finetuned using an identical lightweight MLP head. Our study uncovers two previously overlooked factors: (1) SigLIP2 consistently achieves strong performance; and (2) the choice of activation function plays a surprisingly crucial role, particularly for enhancing the generalization ability of image quality assessment models. Notably, we find that simple sigmoid activations outperform commonly used ReLU and GELU on several benchmarks. Motivated by this finding, we introduce a learnable activation selection mechanism that adaptively determines the nonlinearity for each channel, eliminating the need for manual activation design, and achieving new state-of-the-art SRCC on CLIVE, KADID10K, and AGIQA3K. Extensive ablations confirm the benefits across architectures and regimes, establishing strong, resource-efficient NR-IQA baselines.