10 citations · 21 across the 7 of their papers we have counts for
7 papers · 1 filter
Effective Neural Topic Modeling with Embedding Clustering Regularization
Xiaobao Wu, Xinshuai Dong, Thong Nguyen +1
Topic models have been prevalent for decades with various applications. However, existing topic models commonly suffer from the notorious topic collapsing: discovered topics semant…
Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction
Thong Nguyen, Xiaobao Wu, Xinshuai Dong +4
Multimodal Review Helpfulness Prediction (MRHP) aims to rank product reviews based on predicted helpfulness scores and has been widely applied in e-commerce via presenting customer…
Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions
Thong Nguyen, Xiaobao Wu, Anh-Tuan Luu +3
Modern Review Helpfulness Prediction systems are dependent upon multiple modalities, typically texts and images. Unfortunately, those contemporary approaches pay scarce attention t…
Vision-and-Language Pretraining
Thong Nguyen, Cong-Duy Nguyen, Xiaobao Wu +2
With the burgeoning amount of data of image-text pairs and diversity of Vision-and-Language (V\&L) tasks, scholars have introduced an abundance of deep learning models in this rese…
Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation
Thong Nguyen, Luu Anh Tuan
Current state-of-the-art cross-lingual summarization models employ multi-task learning paradigm, which works on a shared vocabulary module and relies on the self-attention mechanis…
Contrastive Learning for Neural Topic Model
Thong Nguyen, Anh Tuan Luu
Recent empirical studies show that adversarial topic models (ATM) can successfully capture semantic patterns of the document by differentiating a document with another dissimilar s…
Enriching and Controlling Global Semantics for Text Summarization
Thong Nguyen, Anh Tuan Luu, Truc Lu +1
Recently, Transformer-based models have been proven effective in the abstractive summarization task by creating fluent and informative summaries. Nevertheless, these models still s…