J
Jia Wei Chang
Researcher at National Taichung University of Science and Technology
Publications - 36
Citations - 477
Jia Wei Chang is an academic researcher from National Taichung University of Science and Technology. The author has contributed to research in topics: Computer science & Semantic similarity. The author has an hindex of 6, co-authored 27 publications receiving 245 citations. Previous affiliations of Jia Wei Chang include National Cheng Kung University.
Papers
More filters
Journal ArticleDOI
Adaptive Deep Learning-Based Air Quality Prediction Model Using the Most Relevant Spatial-Temporal Relations
TL;DR: The proposed predictive model considers various meteorology data from the previous few hours as well as information related to the elevation space to extract terrain impact on air quality and achieves excellent performance and outperforms current state-of-the-art methods.
Journal ArticleDOI
A Grammar-Based Semantic Similarity Algorithm for Natural Language Sentences
TL;DR: A sentence similarity algorithm that takes advantage of corpus-based ontology and grammatical rules to overcome the addressed problems and has a significant performance improvement in sentences/short-texts with arbitrary syntax and structure is proposed.
Journal ArticleDOI
Integrating a semantic-based retrieval agent into case-based reasoning systems
TL;DR: A novel framework for a case-based reasoning system that includes a collaborative filtering mechanism and a semantic-based case retrieval agent is presented that outperforms most previously described approaches.
Journal ArticleDOI
Enabling Intelligent Environment by the Design of Emotionally Aware Virtual Assistant: A Case of Smart Campus
TL;DR: A Deep Neural Network (DNN) based emotionally aware campus virtual assistant that provides a simple voice response interface, without the need for users to find information in complex web pages or app menus.
Proceedings ArticleDOI
Disentangling Long and Short-Term Interests for Recommendation
TL;DR: A Contrastive learning framework to disentangle Long and Short-term interests for Recommendation (CLSR) with self-supervision with pairwise contrastive tasks designed to supervise the similarity between interest representations and their corresponding interest proxies.