69 citations · 220 across the 37 of their papers we have counts for
22 papers · 1 filter
UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis
Dou Hu, Lingwei Wei, Yaxin Liu +2
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 li…
CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval
Guangyuan Ma, Xing Wu, Peng Wang +1
Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation b…
CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval
Xing Wu, Guangyuan Ma, Peng Wang +4
Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-e…
InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings
Xing Wu, Chaochen Gao, Zijia Lin +3
Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer. The constrai…
ConTextual Masked Auto-Encoder for Dense Passage Retrieval
Xing Wu, Guangyuan Ma, Meng Lin +3
Dense passage retrieval aims to retrieve the relevant passages of a query from a large corpus based on dense representations (i.e., vectors) of the query and the passages. Recent s…
Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion-Cause Pair Extraction
Yinan Bao, Qianwen Ma, Lingwei Wei +2
The Emotion-Cause Pair Extraction (ECPE) task aims to extract emotions and causes as pairs from documents. We observe that the relative distance distribution of emotions and causes…
Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks
Xing Wu, Chaochen Gao, Meng Lin +3
Before entering the neural network, a token is generally converted to the corresponding one-hot representation, which is a discrete distribution of the vocabulary. Smoothed represe…
ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding
Xing Wu, Chaochen Gao, Liangjun Zang +3
Contrastive learning has been attracting much attention for learning unsupervised sentence embeddings. The current state-of-the-art unsupervised method is the unsupervised SimCSE (…
Smoothed Contrastive Learning for Unsupervised Sentence Embedding
Xing Wu, Chaochen Gao, Yipeng Su +3
Contrastive learning has been gradually applied to learn high-quality unsupervised sentence embedding. Among the previous un-supervised methods, the latest state-of-the-art method,…
SRLF: A Stance-aware Reinforcement Learning Framework for Content-based Rumor Detection on Social Media
Chunyuan Yuan, Wanhui Qian, Qianwen Ma +2
The rapid development of social media changes the lifestyle of people and simultaneously provides an ideal place for publishing and disseminating rumors, which severely exacerbates…
Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users Based on Weakly Supervised Learning
Chunyuan Yuan, Qianwen Ma, Wei Zhou +2
The dissemination of fake news significantly affects personal reputation and public trust. Recently, fake news detection has attracted tremendous attention, and previous studies ma…
Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis
Lingwei Wei, Dou Hu, Wei Zhou +5
Document-level Sentiment Analysis (DSA) is more challenging due to vague semantic links and complicate sentiment information. Recent works have been devoted to leveraging text summ…
Pre-training Text Representations as Meta Learning
Shangwen Lv, Yuechen Wang, Daya Guo +10
Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training…
Data Augmentation for Copy-Mechanism in Dialogue State Tracking
Xiaohui Song, Liangjun Zang, Yipeng Su +3
While several state-of-the-art approaches to dialogue state tracking (DST) have shown promising performances on several benchmarks, there is still a significant performance gap bet…
Beyond Statistical Relations: Integrating Knowledge Relations into Style Correlations for Multi-Label Music Style Classification
Qianwen Ma, Chunyuan Yuan, Wei Zhou +2
Automatically labeling multiple styles for every song is a comprehensive application in all kinds of music websites. Recently, some researches explore review-driven multi-label mus…
Jointly embedding the local and global relations of heterogeneous graph for rumor detection
Chunyuan Yuan, Qianwen Ma, Wei Zhou +2
The development of social media has revolutionized the way people communicate, share information and make decisions, but it also provides an ideal platform for publishing and sprea…
Learning review representations from user and product level information for spam detection
Chunyuan Yuan, Wei Zhou, Qianwen Ma +3
Opinion spam has become a widespread problem in social media, where hired spammers write deceptive reviews to promote or demote products to mislead the consumers for profit or fame…
TransSent: Towards Generation of Structured Sentences with Discourse Marker
Xing Wu, Dongjun Wei, Liangjun Zang +2
Structured sentences are important expressions in human writings and dialogues. Previous works on neural text generation fused semantic and structural information by encoding the e…
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
Shangwen Lv, Daya Guo, Jingjing Xu +7
Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evid…
"Mask and Infill" : Applying Masked Language Model to Sentiment Transfer
Xing Wu, Tao Zhang, Liangjun Zang +2
This paper focuses on the task of sentiment transfer on non-parallel text, which modifies sentiment attributes (e.g., positive or negative) of sentences while preserving their attr…
Imbalanced Sentiment Classification Enhanced with Discourse Marker
Tao Zhang, Xing Wu, Meng Lin +2
Imbalanced data commonly exists in real world, espacially in sentiment-related corpus, making it difficult to train a classifier to distinguish latent sentiment in text data. We ob…
Conditional BERT Contextual Augmentation
Xing Wu, Shangwen Lv, Liangjun Zang +2
We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfittin…