A Topic-Aware Reinforced Model for Weakly Supervised Stance Detection
Explore this paper's citation graph
Summary
A Topic-Aware Reinforced Model (TARM) for weakly supervised stance detection is proposed, which consists of a detection network that incorporates target-related topic information into representation learning for identifying stance effectively and a policy network that learns to eliminate noisy instances from auto-labeled data based on off-policy reinforcement learning.
- Type
- article
- Published
- 2019-07-17
- Cited by
- 24
- References
- 37
- Access
- Open access
- OpenAlex
- https://openalex.org/W2903978737
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:58212989
Keywords
Reinforcement learning, Computer science, Machine learning, Artificial intelligence, Representation (politics)
References
- Get out the vote: Determining support or opposition from Congressional floor-debate transcripts
- BTM: Topic Modeling over Short Texts
- Reasoning about Entailment with Neural Attention
- Extra-Linguistic Constraints on Stance Recognition in Ideological Debates
- Recognizing Stances in Online Debates
- Distributed Representations of Words and Phrases and their Compositionality
- Policy Gradient Methods for Reinforcement Learning with Function Approximation
- Stance Detection with Bidirectional Conditional Encoding
- MITRE at SemEval-2016 Task 6: Transfer Learning for Stance Detection
- SemEval-2016 Task 6: Detecting Stance in Tweets
- pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection
- Weakly Supervised Tweet Stance Classification by Relational Bootstrapping
- A Joint Sentiment-Target-Stance Model for Stance Classification in Tweets
- Sentiment Analysis and Opinion Mining
- Proximal Policy Optimization Algorithms
- Distantly Supervised Lifelong Learning for Large-Scale Social Media Sentiment Analysis
- Stance Classification with Target-specific Neural Attention
- Reinforcement Learning for Relation Classification From Noisy Data
- Topical Stance Detection for Twitter: A Two-Phase LSTM Model Using Attention
- Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM
Cited by
- Dissecting Twitter Discussion Threads with Topic-Aware Network Visualization
- Stance Detection on Social Media: State of the Art and Trends
- Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association
- Stance Detection in COVID-19 Tweets
- Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph
- A spatial-temporal topic model with sparse prior and RNN prior for bursty topic discovering in social networks
- STEM: Unsupervised STructural EMbedding for Stance Detection
- ConPhrase: Enhancing Context-Aware Phrase Mining From Text Corpora
- MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmark
- A systematic review of machine learning techniques for stance detection and its applications
- Review of stance detection for rumor verification in social media
- A novel topic clustering algorithm based on graph neural network for question topic diversity
- Zero-shot stance detection via multi-perspective contrastive learning with unlabeled data
- Topic modeling methods for short texts: A survey
- SSSD: Leveraging Pre-trained Models and Semantic Search for Semi-supervised Stance Detection
- Contextual Target-Specific Stance Detection on Twitter: Dataset and Method
- Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models
- A Survey of Stance Detection on Social Media: New Directions and Perspectives
- Caskow: Context-Aware Stance Detection Using External Knowledge-Augmented LLM
- Deep Learning in Stance Detection: A Survey
Related papers
- An Overview of Machine Learning, Deep Learning, and Reinforcement Learning-Based Techniques in Quantitative Finance: Recent Progress and Challenges
- Guided Self-Training based Semi-Supervised Learning for Fraud Detection
- Semi-supervised Domain Adaptation via adversarial training
- Co-Labeling for Multi-View Weakly Labeled Learning
- Sentiment Prediction by a Classifier
- Weaker Than You Think: A Critical Look at Weakly Supervised Learning