Hi! I am Luu Anh Tuan, an Assistant Professor at School of Computer Science and Engineering, Nanyang Technological University. Before that, I was a postdoctoral fellow at MIT CSAIL and a member of the Natural Language Processing group under the supervision of Prof. Regina Barzilay from 2018 to 2020. I obtained Ph.D. degree in computer engineering from Nanyang Technological University in 2016. From 2016 to 2018, I was a research scientist at Institute for Infocomm Research, Singapore in the Natural Language Processing group of Dr. Jian Su.
My research interests lie in the intersection of Artificial Intelligence and Natural Language Processing with the focus on applications of pretrained language models, semantics, question & answering, information extraction and knowledge construction, robustness & trustworthy AI, and recommendation systems.
Interests
- Artificial Intelligence
- Natural Language Processing
Latest
- Don’t Forget Your Reward Values: Language Model Alignment via Value-based Calibration
- Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models
- Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
- Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
- Who’s Who: Large Language Models Meet Knowledge Conflicts in Practice
- SoVAR: Build Generalizable Scenarios from Accident Reports for Autonomous Driving Testing
- Data Augmentation using LLMs: Data Perspectives, Learning Paradigms and Challenges
- Exploring the Potential of Large Language Models in Computational Argumentation
- Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
- Towards the TopMost: A Topic Modeling System Toolkit
- UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages
- Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
- Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
- Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
- Historical Embedding-Guided Efficient Large-Scale Federated Graph Learning
- KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning
- KDMCSE: Knowledge Distillation Multimodal Sentence Embeddings with Adaptive Angular margin Contrastive Learning
- SemRoDe: Macro Adversarial Training to Learn Representations that are Robust to Word-Level Attacks
- ToXCL: A Unified Framework for Toxic Speech Detection and Explanation
- A Contrastive Learning Framework for Event Detection via Semantic Type Prototype Representation Modeling
- A Novel, Cognitively Inspired, Unified Graph-based Multi-Task Framework for Information Extraction
- Effective Neural Topic Modeling with Embedding Clustering Regularization
- Unlocking the Potential of User Feedback:Leveraging Large Language Model as User Simulators to Enhance Dialogue System
- Using Punctuation as an Adversarial Attack on Deep Learning-Based NLP Systems:An Empirical Study
- A Brief Survey on Recent Advances in Coreference Resolution
- Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment
- Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction
- Jointprop:Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation
- Multi-Scale Receptive Field Graph Model for Emotion Recognition in Conversations
- Zero-Shot Text Classification via Self-Supervised Tuning
- InfoCTM:A Mutual Information Maximization Perspective of Cross-lingual Topic Modeling
- Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Prediction
- Attentive Gated Lexicon Reader with Contrastive Contextual Co-Attention for Sentiment Classification
- Audio-Visual Domain Adaptation Feature Fusion for Speech Emotion Recognition
- Is Discourse Role Important for Emotion Recognition in Conversation?
- Long Range Graph Benchmark
- Certified Robustness Against Natural Language Attacks by Causal Intervention
- Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning
- Recipe for a General, Powerful, Scalable Graph Transformer
- Textual Manifold-based Defense Against Natural Language Adversarial Examples
- How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
- Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation
- Contrastive Learning for Neural Topic Model
- Graph Neural Networks with Learnable Structural and Positional Representations
- Towards Robustness Against Natural Language Word Substitutions
- Beyond Fully-Connected Layers with Quaternions:Parameterization of Hypercomplex Multiplications with 1/n Parameters
- Deep Learning to Estimate RECIST in Patients with NSCLC Treated with PD-1 Blockade
- Enriching and Controlling Global Semantics for Text Summarization
- Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences
- Benchmarking Graph Neural Networks
- Capturing Greater Context for Question Generation
- Light and Efficient Neural Natural Language Processing with Quaternion Networks
- Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
- Compositional De-Attention Networks
- Holographic Factorization Machines for Recommendation
- Densely Connected Attention Propagation for Reading Comprehension
- Holistic Multi-modal Memory Network for Movie Question Answering
- Recurrently Controlled Recurrent Networks
- Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences
- Multi-Cast Attention Networks for Retrieval-based Question Answering and Response Prediction
- CoupleNet:Paying Attention to Couples with Coupled Attention for Relationship Recommendation
- Hermitian Co-Attention Networks for Text Matching in Asymmetrical Domains
- Compare, Compress and Propagate:Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference
- Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension
- Multi-Pointer Co-Attention Networks for Recommendation
- Reasoning with Sarcasm by Reading In-between
- Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis
- Cross Temporal Recurrent Networks for Ranking Question Answer Pairs
- Dyadic Memory Networks for Aspect-based Sentiment Analysis
- SkipFlow:Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring
- Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering
- Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking
- Learning to Rank Question Answer Pairs with Holographic Dual LSTM Architecture
- Non-Parametric Estimation of Multiple Embeddings for Link Prediction on Dynamic Knowledge Graphs
- Random Semantic Tensor Ensemble for Scalable Knowledge Graph Link Prediction
- Utilizing Temporal Information for Taxonomy Construction
- Learning Term Embeddings for Taxonomic Relation Identification with Dynamic Weighting Neural Network
- Overview of the Gene Ontology Task at BioCreative IV
- Taxonomy Construction using Syntactic Contextual Evidence
- Incorporating Trustiness and Collective Synonym/ Contrastive Evidence into Taxonomy Construction
- Automatic Suggestion for PUBMED Query Reformulation
- SeVe - Automatic Tool for Verification of Security Protocols