Publications by authors named "Songlei Jian"
Article Synopsis
- Multimodal classification algorithms are used in machine learning to sort different types of data by looking at various features from different sources.
- Researchers created a new system called UMCF that can handle many types of classification tasks without being stuck to just one, and it can adapt to different kinds of data.
- In tests, UMCF did better than other methods in classifying fake news and sentiment analysis, improving results by 2.3% on average.
Categorical data are ubiquitous in machine learning tasks, and the representation of categorical data plays an important role in the learning performance. The heterogeneous coupling relationships between features and feature values reflect the characteristics of the real-world categorical data which need to be captured in the representations. The paper proposes an enhanced categorical data embedding method, i.
View Article and Find Full Text PDF