Cornelia Caragea

On the Calibration of Image Semi-Supervised Learning Models AAAI 2026 MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction EACL 2026 LLM-Guided Co-Training for Text Classification EMNLP 2025 Model Calibration for Emotion Detection EMNLP 2025 Active Few-Shot Learning for Text Classification NAACL 2025 Bilingual Zero-Shot Stance Detection ACL 2025 DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition NAACL 2025 Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-sample Aggregation on Large Language Models NAACL 2025 Hard Emotion Test Evaluation Sets for Language Models NAACL 2025 A MISMATCHED Benchmark for Scientific Natural Language Inference ACL 2025 MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification EMNLP 2025 SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions COLING 2024 EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM NAACL 2024 Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion NAACL 2024 A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus ACL 2024 Co-training for Low Resource Scientific Natural Language Inference ACL 2024 GunStance: Stance Detection for Gun Control and Gun Regulation ACL 2024 EZ-STANCE: A Large Dataset for English Zero-Shot Stance Detection ACL 2024 ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction ACL 2024 ZeroStance: Leveraging ChatGPT for Open-Domain Stance Detection via Dataset Generation ACL 2024 MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference NAACL 2024 Sarcasm Detection in a Disaster Context COLING 2024 Stanceformer: Target-Aware Transformer for Stance Detection EMNLP 2024 VerifyMatch: A Semi-Supervised Learning Paradigm for Natural Language Inference with Confidence-Aware MixUp EMNLP 2024 SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents EMNLP 2024 How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics EMNLP 2024 Semi-Supervised Domain Adaptation for Emotion-Related Tasks ACL 2023 Data Augmentation for Low-Resource Keyphrase Generation ACL 2023 What Clued the AI Doctor In? On the Influence of Data Source and Quality for Transformer-Based Medical Self-Disclosure Detection EACL 2023 Monotonic Location Attention for Length Generalization ICML 2023 Beam Tree Recursive Cells ICML 2023 Efficient Beam Tree Recursion NIPS 2023 Label Smoothing for Emotion Detection (Student Abstract) AAAI 2023 MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins CVPR 2023 DeepZensols: A Deep Learning Natural Language Processing Framework for Experimentation and Reproducibility EMNLP 2023 DeCrisisMB: Debiased Semi-Supervised Learning for Crisis Tweet Classification via Memory Bank EMNLP 2023 Multi-Task Knowledge Distillation with Embedding Constraints for Scholarly Keyphrase Boundary Classification EMNLP 2023 JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification EMNLP 2023 Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability NIPS 2023 Towards Identifying Fine-Grained Depression Symptoms from Memes ACL 2023 Unsupervised Extractive Summarization of Emotion Triggers ACL 2023 A New Direction in Stance Detection: Target-Stance Extraction in the Wild ACL 2023 C-STANCE: A Large Dataset for Chinese Zero-Shot Stance Detection ACL 2023 Distilling Calibrated Knowledge for Stance Detection ACL 2023 Feature Normalization and Cartography-Based Demonstrations for Prompt-Based Fine-Tuning on Emotion-Related Tasks AAAI 2023 Leveraging Training Dynamics and Self-Training for Text Classification EMNLP 2022 Why Do You Feel This Way? Summarizing Triggers of Emotions in Social Media Posts EMNLP 2022 Calibrating Student Models for Emotion-related Tasks EMNLP 2022 Keyphrase Generation Beyond the Boundaries of Title and Abstract EMNLP 2022 KPDROP: Improving Absent Keyphrase Generation EMNLP 2022 On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency ACL 2022 A Data Cartography based MixUp for Pre-trained Language Models NAACL 2022 Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference EMNLP 2022 Multimodal Semi-supervised Learning for Disaster Tweet Classification COLING 2022 Towards Summarizing Healthcare Questions in Low-Resource Setting COLING 2022 A New Public Corpus for Clinical Section Identification: MedSecId COLING 2022 SciNLI: A Corpus for Natural Language Inference on Scientific Text ACL 2022 Hierarchical Multi-Label Classification of Scientific Documents EMNLP 2022 P-Stance: A Large Dataset for Stance Detection in Political Domain IJCNLP 2021 It Takes Two to Empathize: One to Seek and One to Provide AAAI 2021 Author Homepage Discovery in CiteSeerX AAAI 2021 Stance Detection in COVID-19 Tweets ACL 2021 eMLM: A New Pre-training Objective for Emotion Related Tasks ACL 2021 Studying the Evolution of Scientific Topics and their Relationships ACL 2021 A Multi-Task Learning Framework for Multi-Target Stance Detection ACL 2021 P-Stance: A Large Dataset for Stance Detection in Political Domain ACL 2021 Exploiting Position and Contextual Word Embeddings for Keyphrase Extraction from Scientific Papers EACL 2021 Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation EMNLP 2021 Distilling Knowledge for Empathy Detection EMNLP 2021 Modeling Hierarchical Structures with Continuous Recursive Neural Networks ICML 2021 Stance Detection in COVID-19 Tweets IJCNLP 2021 eMLM: A New Pre-training Objective for Emotion Related Tasks IJCNLP 2021 Studying the Evolution of Scientific Topics and their Relationships IJCNLP 2021 A Multi-Task Learning Framework for Multi-Target Stance Detection IJCNLP 2021 Target-Aware Data Augmentation for Stance Detection NAACL 2021 Identifying Medical Self-Disclosure in Online Communities NAACL 2021 Detecting Perceived Emotions in Hurricane Disasters ACL 2020 A Multi-Task Learning Approach to Sarcasm Detection (Student Abstract) AAAI 2020 Exploring Abstract Concepts for Image Privacy Prediction in Social Networks (Student Abstract) AAAI 2020 On Identifying Hashtags in Disaster Twitter Data AAAI 2020 Scientific Keyphrase Identification and Classification by Pre-Trained Language Models Intermediate Task Transfer Learning COLING 2020 Cross-Lingual Disaster-related Multi-label Tweet Classification with Manifold Mixup ACL 2020 On the Use of Web Search to Improve Scientific Collections EMNLP 2020 CancerEmo: A Dataset for Fine-Grained Emotion Detection EMNLP 2020 The Myth of Double-Blind Review Revisited: ACL vs. EMNLP IJCNLP 2019 Dynamically Identifying Deep Multimodal Features for Image Privacy Prediction AAAI 2019 Cleaning Noisy and Heterogeneous Metadata for Record Linking across Scholarly Big Datasets AAAI 2019 Multi-Task Stance Detection with Sentiment and Stance Lexicons IJCNLP 2019 Multi-Task Stance Detection with Sentiment and Stance Lexicons EMNLP 2019 The Myth of Double-Blind Review Revisited: ACL vs. EMNLP EMNLP 2019 Exploring Optimism and Pessimism in Twitter Using Deep Learning EMNLP 2018 Fine-Grained Emotion Detection in Health-Related Online Posts EMNLP 2018 PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents ACL 2017 A Group-Based Personalized Model for Image Privacy Classification and Labeling IJCAI 2017 Identifying Empathetic Messages in Online Health Communities IJCNLP 2017 Content-Driven Detection of Cyberbullying on the Instagram Social Network IJCAI 2016 Supervised Keyphrase Extraction as Positive Unlabeled Learning EMNLP 2016 Co-Training for Topic Classification of Scholarly Data EMNLP 2015 Citation-Enhanced Keyphrase Extraction from Research Papers: A Supervised Approach EMNLP 2014 Identifying Emotional and Informational Support in Online Health Communities COLING 2014 Thread Specific Features are Helpful for Identifying Subjectivity Orientation of Online Forum Threads COLING 2012