MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning
Cross-lingual named entity recognition (CrossNER) faces challenges stemming from
uneven performance due to the scarcity of multilingual corpora, especially for non-English …
uneven performance due to the scarcity of multilingual corpora, especially for non-English …
PMAES: Prompt-mapping contrastive learning for cross-prompt automated essay scoring
Y Chen, X Li - Proceedings of the 61st Annual Meeting of the …, 2023 - aclanthology.org
Current cross-prompt automated essay scoring (AES) is a challenging task due to the large
discrepancies between different prompts, such as different genres and expressions. The …
discrepancies between different prompts, such as different genres and expressions. The …
A cross-guidance cross-lingual model on generated parallel corpus for classical Chinese machine reading comprehension
Chinese diachronic gap is a key issue in classical Chinese machine reading
comprehension (CCMRC). Preceding work on bridging this gap has been mostly restricted …
comprehension (CCMRC). Preceding work on bridging this gap has been mostly restricted …
Multi-level cross-modal contrastive learning for review-aware recommendation
Y Wei, Y Xu, L Zhu, J Ma, C Peng - Expert Systems with Applications, 2024 - Elsevier
Recent studies tend to employ Contrastive Learning (CL) methods to facilitate model training
by extracting self-supervised signals to mitigate data sparsity. However, existing CL-based …
by extracting self-supervised signals to mitigate data sparsity. However, existing CL-based …
FUMMER: A fine-grained self-supervised momentum distillation framework for multimodal recommendation
Y Wei, Y Xu, L Zhu, J Ma, J Huang - Information Processing & Management, 2024 - Elsevier
The considerable semantic information contained in multimodal data is increasingly
appreciated by industry and academia. To effectively leverage multimodal information …
appreciated by industry and academia. To effectively leverage multimodal information …
Diffusion Model-based Contrastive Learning for Human Activity Recognition
C Xiao, Y Han, W Yang, Y Hou, F Shi… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
WiFi Channel State Information (CSI)-based activity recognition has sparked numerous
studies due to its widespread availability and privacy protection. However, when applied in …
studies due to its widespread availability and privacy protection. However, when applied in …
Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfer
J Zheng, F Fan, J Li - arXiv preprint arXiv:2404.16627, 2024 - arxiv.org
Unsupervised cross-lingual transfer involves transferring knowledge between languages
without explicit supervision. Although numerous studies have been conducted to improve …
without explicit supervision. Although numerous studies have been conducted to improve …
[PDF][PDF] The Language Model, Resources, and Computational Pipelines for the Under-Resourced Iranian Azerbaijani
Iranian Azerbaijani is a dialect of the Azerbaijani language spoken by more than 16% of the
population in Iran (> 14 million). Unfortunately, a lack of computational resources is one of …
population in Iran (> 14 million). Unfortunately, a lack of computational resources is one of …
PLAES: Prompt-generalized and Level-aware Learning Framework for Cross-prompt Automated Essay Scoring
Y Chen, X Li - Proceedings of the 2024 Joint International …, 2024 - aclanthology.org
Current cross-prompt automatic essay scoring (AES) systems are primarily concerned with
obtaining shared knowledge specific to the target prompt by using the source and target …
obtaining shared knowledge specific to the target prompt by using the source and target …
Fine-Grained Category Generation for Sets of Entities
Category systems play an essential role in knowledge bases by groupings of semantically
related entities. Category generation task aims to produce category suggestions which can …
related entities. Category generation task aims to produce category suggestions which can …