21 citations · 63 across the 8 of their papers we have counts for
8 papers
Multilingual Search with Subword TF-IDF
Artit Wangperawong
Multilingual search can be achieved with subword tokenization. The accuracy of traditional TF-IDF approaches depend on manually curated tokenization, stop words and stemming rules,…
Transfer Learning Robustness in Multi-Class Categorization by Fine-Tuning Pre-Trained Contextualized Language Models
Xinyi Liu, Artit Wangperawong
This study compares the effectiveness and robustness of multi-class categorization of Amazon product data using transfer learning on pre-trained contextualized language models. Spe…
Question Generation by Transformers
Kettip Kriangchaivech, Artit Wangperawong
A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers, an attention-based model eschewing the paradigm of existing r…
Multi-Label Product Categorization Using Multi-Modal Fusion Models
Pasawee Wirojwatanakul, Artit Wangperawong
In this study, we investigated multi-modal approaches using images, descriptions, and titles to categorize e-commerce products on Amazon. Specifically, we examined late fusion mode…
Attending to Mathematical Language with Transformers
Artit Wangperawong
Mathematical expressions were generated, evaluated and used to train neural network models based on the transformer architecture. The expressions and their targets were analyzed as…
A Collaborative Approach to Angel and Venture Capital Investment Recommendations
Xinyi Liu, Artit Wangperawong
Matrix factorization was used to generate investment recommendations for investors. An iterative conjugate gradient method was used to optimize the regularized squared-error loss f…
Comparing heterogeneous entities using artificial neural networks of trainable weighted structural components and machine-learned activation functions
Artit Wangperawong, Kettip Kriangchaivech, Austin Lanari +2
To compare entities of differing types and structural components, the artificial neural network paradigm was used to cross-compare structural components between heterogeneous docum…
Churn analysis using deep convolutional neural networks and autoencoders
Artit Wangperawong, Cyrille Brun, Olav Laudy +1
Customer temporal behavioral data was represented as images in order to perform churn prediction by leveraging deep learning architectures prominent in image classification. Superv…