Supervised adversarial contrastive learning for emotion recognition in conversations

D Hu, Y Bao, L Wei, W Zhou, S Hu - arxiv preprint arxiv:2306.01505, 2023 - arxiv.org
Extracting generalized and robust representations is a major challenge in emotion
recognition in conversations (ERC). To address this, we propose a supervised adversarial …

Modeling both intra-and inter-modality uncertainty for multimodal fake news detection

L Wei, D Hu, W Zhou, S Hu - IEEE Transactions on Multimedia, 2023 - ieeexplore.ieee.org
Multimodal fake news detection has obtained increasing attention recently. Existing works
generally encode multimodal contents into a deterministic point in semantic subspaces, and …

[PDF][PDF] Neural Natural Language Processing for long texts: A survey of the state-of-the-art

D Tsirmpas, I Gkionis, I Mademlis - Ar**v Prepr. Ar**v230516259, 2023 - academia.edu
Abstract The adoption of Deep Neural Networks (DNNs) has greatly benefited Natural
Language Processing (NLP) during the past decade. However, the demands of long …

Varmae: Pre-training of variational masked autoencoder for domain-adaptive language understanding

D Hu, X Hou, X Du, M Zhou, L Jiang, Y Mo… - arxiv preprint arxiv …, 2022 - arxiv.org
Pre-trained language models have achieved promising performance on general
benchmarks, but underperform when migrated to a specific domain. Recent works perform …

Support towards emergency event processing via fine-grained analysis on users' expressions

Q Zhou - Aslib Journal of Information Management, 2024 - emerald.com
Purpose With the rapid development of social media, the occurrence and evolution of
emergency events are often accompanied by massive users' expressions. The fine-grained …

PALI-NLP at SemEval-2022 Task 4: Discriminative Fine-tuning of Transformers for Patronizing and Condescending Language Detection

D Hu, M Zhou, X Du, M Yuan, M **, L Jiang… - arxiv preprint arxiv …, 2022 - arxiv.org
Patronizing and condescending language (PCL) has a large harmful impact and is difficult to
detect, both for human judges and existing NLP systems. At SemEval-2022 Task 4, we …

UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis

D Hu, L Wei, Y Liu, W Zhou, S Hu - arxiv preprint arxiv:2306.01093, 2023 - arxiv.org
This paper describes our system designed for SemEval-2023 Task 12: Sentiment analysis
for African languages. The challenge faced by this task is the scarcity of labeled data and …

An Efficient Aspect-based Sentiment Classification with Hybrid Word Embeddings and CNN Framework

M Agrawal, NR Moparthi - International Journal of Sensors …, 2024 - benthamdirect.com
Background: As the e-commerce product reviews and social media posts are increasing
enormously, the size of the database for polarity/sentiment detection is a challenging task …

Position-Wise Gated Res2Net-Based Convolutional Network with Selective Fusing for Sentiment Analysis

J Zhou, X Zeng, Y Zou, H Zhu - Entropy, 2023 - mdpi.com
Sentiment analysis (SA) is an important task in natural language processing in which
convolutional neural networks (CNNs) have been successfully applied. However, most …