7 papers
Structure and Destructure: Dual Forces in the Making of Knowledge Engines
Yihong Chen
The making of knowledge engines in natural language processing has been shaped by two seemingly distinct paradigms: one grounded in structure, the other driven by massively availab…
Distance-aware Self-adaptive Graph Convolution for Fine-grained Hierarchical Recommendation
Tao Huang, Yihong Chen, Wei Fan +2
Graph Convolutional Networks (GCNs) are widely used to improve recommendation accuracy and performance by effectively learning the representations of user and item nodes. However,…
Probing In-Context Learning: Impact of Task Complexity and Model Architecture on Generalization and Efficiency
Binwen Liu, Peiyu Xu, Quan Yuan +1
We investigate in-context learning (ICL) through a meticulous experimental framework that systematically varies task complexity and model architecture. Extending beyond the linear…
Multilingual Language Model Pretraining using Machine-translated Data
Jiayi Wang, Yao Lu, Maurice Weber +5
High-resource languages such as English, enables the pretraining of high-quality large language models (LLMs). The same can not be said for most other languages as LLMs still under…
AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
Chunan Liu, Lilian Denzler, Yihong Chen +2
Epitope identification is vital for antibody design yet challenging due to the inherent variability in antibodies. While many deep learning methods have been developed for general…
Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language
Jiayi Wang, Yao Lu, Maurice Weber +4
English, as a very high-resource language, enables the pretraining of high-quality large language models (LLMs). The same cannot be said for most other languages, as leading LLMs s…