A brief overview of universal sentence representation methods: A linguistic view

R Li, X Zhao, MF Moens - ACM Computing Surveys (CSUR), 2022 - dl.acm.org
How to transfer the semantic information in a sentence to a computable numerical
embedding form is a fundamental problem in natural language processing. An informative …

Evaluating embeddings from pre-trained language models and knowledge graphs for educational content recommendation

X Li, A Henriksson, M Duneld, J Nouri, Y Wu - Future Internet, 2023 - mdpi.com
Educational content recommendation is a cornerstone of AI-enhanced learning. In particular,
to facilitate navigating the diverse learning resources available on learning platforms …

Convolution–deconvolution word embedding: An end-to-end multi-prototype fusion embedding method for natural language processing

K Shuang, Z Zhang, J Loo, S Su - Information Fusion, 2020 - Elsevier
Existing unsupervised word embedding methods have been proved to be effective to
capture latent semantic information on various tasks of Natural Language Processing (NLP) …

A novel model for imbalanced data classification

J Yin, C Gan, K Zhao, X Lin, Z Quan, ZJ Wang - Proceedings of the AAAI …, 2020 - aaai.org
Recently, imbalanced data classification has received much attention due to its wide
applications. In the literature, existing researches have attempted to improve the …

A neural knowledge graph evaluator: Combining structural and semantic evidence of knowledge graphs for predicting supportive knowledge in scientific QA

C Qiao, X Hu - Information Processing & Management, 2020 - Elsevier
Effectively detecting supportive knowledge of answers is a fundamental step towards
automated question answering. While pre-trained semantic vectors for texts have enabled …

A knowledge-enriched ensemble method for word embedding and multi-sense embedding

L Fang, Y Luo, K Feng, K Zhao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Representing words as embeddings has been proven to be successful in improving the
performance in many natural language processing tasks. Different from the traditional …

Generalized ambiguity decomposition for ranking ensemble learning

H Liu, Y Du, Z Wu - Journal of Machine Learning Research, 2022 - jmlr.org
Error decomposition analysis is a key problem for ensemble learning, which indicates that
proper combination of multiple models can achieve better performance than any individual …

A Hybrid Approach for Binary Classification of Imbalanced Data

H Tsai, TW Yang, WM Wong, HY Kao… - International Journal of …, 2024 - World Scientific
Binary classification with an imbalanced dataset is challenging. Models tend to consider all
samples as belonging to the majority class. Although existing solutions such as sampling …

Effective Diversity Optimizations for High Accuracy Deep Ensembles

H **, MA Aghdam, SNC Medikonduru… - 2024 IEEE 6th …, 2024 - ieeexplore.ieee.org
Deep Neural Network Ensembles (Deep Ensembles) have emerged as a popular technique
for enhancing overall prediction accuracy by leveraging the complementary predictive …

Multilingual music genre embeddings for effective cross-lingual music item annotation

EV Epure, G Salha, R Hennequin - arxiv preprint arxiv:2009.07755, 2020 - arxiv.org
Annotating music items with music genres is crucial for music recommendation and
information retrieval, yet challenging given that music genres are subjective concepts …