|
I am an Assistant Professor in the Department of Computer and Information Science
at the University of Oregon. I obtained my Ph.D. and M.S. degrees in Computer Science from New York University (working with Ralph Grishman and Kyunghyun Cho),
and my B.S. degree in Computer Science from Hanoi University of Science and Technology. I was also a postdoc in the University of Montréal, working with Yoshua Bengio and people in the Montreal Institute for Learning Algorithms.
RESEARCH
My research explores mechanisms to understand human languages for computers so that computers can perform cognitive language-related tasks for us. Among others, I am especially interested in distilling structured information and mining useful knowledge from massive and multilingual human-written text of various domains.
Toward this end, our lab employs and designs effective learning algorithms for information extraction and text mining in natural language processing and data mining. We are currently focusing on deep learning algorithms to solve such problems. We are among the first groups that develop deep learning models and demonstrate their effectiveness for information extraction.
We are also targeting other language-related problems with deep learning, including reading comprehension, machine translation, natural language generation, chatbots and language grounding.
SOFTWARE
-
FourIE: For a better idea about our research on information extraction, check out a demo for our recent neural information extraction system (performing joint entity mention detection, relation extraction, event detection, and argument role prediction) here.
-
Trankit: a light-weight transformer-based toolkit for multilingual NLP that can process raw text and support fundamental NLP tasks for 56 languages. Trankit is based on recent advances on multilingual pre-trained language models, providing state-of-the-art performance for Sentence Segmentation, Tokenization, Multi-word Token Expansion, POS Tagging, Morphological Feature Tagging, Dependency Parsing, and Named Entity Recognition over 90 Universal Dependencies treebanks. Trankit can be installed and used easily with Python. Check out Trankit's documentation page for installation and usage. We also provide a demo and release the code for Trankit at our github repo.
HIRING
I am currently recruiting one or two graduate students for Fall 2021 to work on interesting projects of natural language processing and deep learning. Interested candidates can email me for more information. The application procedure for graduate students in the Department of Computer and Information Science can be found here.
I am also willing to supervise students at UO who would like to do research on natural language processing, deep learning and the related topics. Please email me if you are interested in this possibility.
PUBLICATIONS
2021
- Graph Learning Regularization and Transfer Learning for Few-Shot Event Detection
Viet Dac Lai, Minh Van Nguyen, Franck Dernoncourt, and Thien Huu Nguyen
Proceedings of SIGIR 2021
[To Appear]    
- Predicting Patient Readmission Risk from Medical Text via Knowledge Graph Enhanced Multiview Graph Convolution
Qiuhao Lu, Thien Huu Nguyen, and Dejing Dou
Proceedings of SIGIR 2021
[To Appear]    
- Dictionary-guided Scene Text Recognition
Nguyen Nguyen, Thu Nguyen, Vinh Tran, Minh-Triet Tran, Thanh Duc Ngo, Thien Huu Nguyen, and Minh Hoai
Proceedings of CVPR 2021
[To Appear]    
- Dynamic Path Reasoning for Measurement Relation Extraction
Amir Pouran Ben Veyseh, Franck Dernoncourt, and Thien Huu Nguyen
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval) at ACL-IJCNLP 2021
[To Appear]    
- Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing
Minh Van Nguyen, Viet Dac Lai, Amir Pouran Ben Veyseh and Thien Huu Nguyen
Proceedings of EACL 2021 (Demonstrations)
[PAPER][Github][Documentation][Demo]    
- Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks
Minh Van Nguyen, Viet Dac Lai and Thien Huu Nguyen
Proceedings of NAACL-HLT 2021
[PAPER]    
- Graph Convolutional Networks for Event Causality Identification with Rich Document-level Structures
Minh Phu Tran and Thien Huu Nguyen
Proceedings of NAACL-HLT 2021
[To Appear]    
- MadDog: A Web-based System for Acronym Identification and Disambiguation
Amir Pouran Ben Veyseh, Franck Dernoncourt, Walter Chang and Thien Huu Nguyen
Proceedings of EACL 2021 (Demonstrations)
[PAPER]    
-
Inducing Rich Interaction Structures between Words for Document-level Event Argument Extraction
Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Hung Tran, Varun Manjunatha, Lidan Wang, Rajiv Jain, Doo Soon Kim, Walter Chang and Thien Huu Nguyen
Proceedings of the 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2021), Delhi, India, May, 2021
[To Appear]    
- Improving Cross-Lingual Transfer for Event Argument Extraction with Language-Universal Sentence Structures
Minh Van Nguyen and Thien Huu Nguyen
Proceedings of the Arabic Natural Language Processing Workshop at EACL 2021
[To Appear]    
- Fine-Grained Event Trigger Detection
Duong Le and Thien Huu Nguyen
Proceedings of EACL 2021
[To Appear]    
- Acronym Identification and Disambiguation Shared Tasks for Scientific Document Understanding
Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen, Walter Chang and Leo Anthony Celi
Proceedings of the Workshop on Scientific Document Understanding at AAAI 2021
[To Appear]    
2020
- What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation
Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Hung Tran and Thien Huu Nguyen
Proceedings of COLING 2020
[PAPER]    
- Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization
Qiuhao Lu, Nisansa de Silva, Dejing Dou, Thien Huu Nguyen, Prithviraj Sen, Berthold Reinwald and Yunyao Li
Proceedings of COLING 2020
[To Appear]    
- Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning
Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Dejing Dou and Thien Huu Nguyen
Proceedings of EMNLP 2020
[PAPER]    
- Introducing a New Dataset for Event Detection in Cybersecurity Texts
Hieu Man Duc Trong, Duc Trong Le, Amir Pouran Ben Veyseh, Thuat Nguyen and Thien Huu Nguyen
Proceedings of EMNLP 2020
[PAPER]    
- Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks
Viet Dac Lai, Tuan Ngo Nguyen and Thien Huu Nguyen
Proceedings of EMNLP 2020
[PAPER]    
- Structural and Functional Decomposition for Personality Image Captioning in a Communication Game
Minh Thu Nguyen, Duy Phung, Minh Hoai and Thien Huu Nguyen
Proceedings of EMNLP 2020 (Findings)
[PAPER]    
- The Dots Have Their Values: Exploiting the Node-Edge Connections in Graph-based Neural Models for Document-level Relation Extraction
Hieu Minh Tran, Minh Trung Nguyen and Thien Huu Nguyen
Proceedings of EMNLP 2020 (Findings)
[PAPER]    
- Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction
Amir Pouran Ben Veyseh, Tuan Ngo Nguyen and Thien Huu Nguyen
Proceedings of EMNLP 2020 (Findings)
[PAPER]    
- Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation
Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Quan Hung Tran, Dejing Dou and Thien Huu Nguyen
Proceedings of EMNLP 2020 (Findings)
[PAPER]    
-
Bag of Biterms Modeling for Short Texts
Anh Tuan Phan, Bach Tran, Thien Huu Nguyen, Linh Van Ngo and Khoat Than
Knowledge and Information Systems Journal (KAIS) 2020
[PAPER]    
-
Improving Slot Filling by Utilizing Contextual Information
Amir Pouran Ben Veyseh, Franck Dernoncourt and Thien Huu Nguyen
Proceedings of the 2nd NLP for Conversational AI Workshop (ConvAI) at ACL 2020, Seattle, USA, July 2020
[PAPER]    
-
Extensively Matching for Few-shot Learning Event Detection
Viet Lai, Franck Dernoncourt and Thien Huu Nguyen
Proceedings of the 1st Joint Workshop on Narrative Understanding, Storylines, and Events (NUSE) at ACL 2020, Seattle, USA, July 2020
[PAPER]    
- Exploiting the Syntax-Model Consistency for Neural Relation Extraction
Amir Pouran Ben Veyseh, Franck Dernoncourt, Dejing Dou and Thien Huu Nguyen
Proceedings of ACL 2020, Seattle, USA, July 2020
[PAPER]    
-
Exploiting the Matching Information in the Support Set for Few Shot Event Classification
Viet Lai, Franck Dernoncourt and Thien Huu Nguyen
Proceedings of the 24th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2020), Singapore, May, 2020
[PAPER]    
-
Learning to Select Important Context Words for Event Detection
Nghia Ngo, Tuan Ngo Nguyen and Thien Huu Nguyen
Proceedings of the 24th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2020), Singapore, May, 2020
[PAPER]    
- Multi-view Consistency for Relation Extraction via Mutual Information and Structure Prediction
Amir Pouran Ben Veyseh, Franck Dernoncourt, My Thai, Dejing Dou and Thien Huu Nguyen
Proceedings of AAAI 2020, New York, USA, February 2020
[PAPER]    
- A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency
Amir Pouran Ben Veyseh, Franck Dernoncourt, Dejing Dou and Thien Huu Nguyen
Proceedings of AAAI 2020, New York, USA, February 2020
[PAPER]    
- Multi-task Learning for Metaphor Detection with Graph Convolutional Neural Networks and Word Sense Disambiguation
Duong Minh Le, My Thai and Thien Huu Nguyen
Proceedings of AAAI 2020, New York, USA, February 2020
[PAPER]    
2019
- On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning
Tuan Ngo Nguyen, Franck Dernoncourt and Thien Huu Nguyen
Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019) at EMNLP 2019
[PAPER]    
- Extending Event Detection to New Types with Learning from Keywords
Viet Lai and Thien Huu Nguyen
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019) at EMNLP 2019
[PAPER]    
- Learning Electronic Health Records through Hyperbolic Embedding
of Medical Ontologies
Qiuhao Lu, Nisansa de Silva, Sabin Kafle, Jiazhen Cao, Dejing
Dou, Thien Huu Nguyen, Prithviraj Sen, Brent Hailpern, Berthold Reinwald and
Yunyao Li
Proceedings of the 10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB 2019), New York, September 2019
[PAPER]    
- Rumor Detection in Social Networks via Deep Contextual Modeling
Amir Pouran Ben Veyseh, My T. Thai, Thien Huu Nguyen and Dejing Dou
Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2019), Vancouver, Canada, August 2019
[PAPER]    
- Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings
Linh The Nguyen, Linh Van Ngo, Khoat Than and Thien Huu Nguyen
Proceedings of ACL 2019, Florence, Italy, August 2019
[PAPER]    
- Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures
Amir Pouran Ben Veyseh, Thien Huu Nguyen and Dejing Dou
Proceedings of ACL 2019, Florence, Italy, August 2019
[PAPER]    
- Improving Cross-Domain Performance for Relation Extraction via Dependency Prediction and Information Flow Control
Amir Pouran Ben Veyseh, Thien Huu Nguyen and Dejing Dou
Proceedings of IJCAI 2019, Macao, China, August 2019
[PAPER]    
- BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop
Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, Lucas Willems, Chitwan Saharia, Thien Huu Nguyen and Yoshua Bengio
Proceedings of ICLR 2019, New Orleans, Louisiana, May 2019
[PAPER]    
- Systematic Generalization: What Is Required and Can It Be Learned?
Dzmitry Bahdanau, Shikhar Murty, Michael Noukhovitch, Thien Huu Nguyen, Harm de Vries and Aaron Courville
Proceedings of ICLR 2019, New Orleans, Louisiana, May 2019
[PAPER]    
- One for All: Neural Joint Modeling of Entities and Events
Trung Minh Nguyen and Thien Huu Nguyen
Proceedings of AAAI 2019, Honolulu, Hawaii, January 2019
[PAPER]    
2018
- A Case Study on Learning a Unified Encoder of Relations
Lisheng Fu, Bonan Min, Thien Huu Nguyen and Ralph Grishman
Proceedings of the 4th Workshop on Noisy User-generated Text (W-NUT 2018) at EMNLP 2018
[PAPER]    
- Similar but not the Same: Word Sense Disambiguation Improves Event Detection via Neural Representation Matching
Weiyi Lu and Thien Huu Nguyen
Proceedings of EMNLP 2018, Brussels, Belgium, November 2018
[PAPER]    
- Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs
Minh Nguyen and Thien Huu Nguyen
Proceedings of COLING 2018, Santa Fe, New-Mexico, August 2018
[PAPER]    
- A Deep Learning Model with Hierarchical LSTMs and Supervised Attention for Anti-Phishing
Minh Nguyen, Toan Nguyen and Thien Huu Nguyen
International Workshop on Security and Privacy Analytics - Anti Phishing Shared Task (IWSPA-AP), March 2018
[PAPER]    
- Graph Convolutional Networks with Argument-Aware Pooling for Event Detection
Thien Huu Nguyen and Ralph Grishman
Proceedings of AAAI 2018, New Orleans, Lousiana, February 2018
[PAPER]    
- Deep Learning for Information Extraction
Thien Huu Nguyen
Ph.D. Thesis, New York University, January 2018.
[PAPER]    
2017
- Domain Adaptation for Relation Extraction with Domain Adversarial Neural Networks
Lisheng Fu, Thien Huu Nguyen, Bonan Min and Ralph Grishman
Proceedings of IJCNLP 2017, Taipei, Taiwan, November 2017
[PAPER]    
2016
-
New York University 2016 System for KBP Event Nugget: A Deep Learning Approach
Thien Huu Nguyen, Adam Meyers and Ralph Grishman
Proceedings of Text Analysis Conference (TAC), Gaithersburg, Maryland, USA, November 2016
[PAPER]
-
Joint Learning of Local and Global Features for Entity Linking via Neural Networks
Thien Huu Nguyen, Nicolas Fauceglia, Mariano Rodriguez Muro, Oktie Hassanzadeh, Alfio Massimiliano Gliozzo and Mohammad Sadoghi
Proceedings of COLING 2016, Osaka, Japan, December 2016
[PAPER]
-
Modeling Skip-Grams for Event Detection with Convolutional Neural Networks
Thien Huu Nguyen and Ralph Grishman
Proceedings of EMNLP 2016, Austin, Texas, November 2016
[PAPER]
-
Joint Event Extraction via Recurrent Neural Networks
Thien Huu Nguyen, Kyunghyun Cho and Ralph Grishman
Proceedings of NAACL 2016, San Diego, June 2016
[PAPER][CODE]
-
A Two-stage Approach for Extending Event Detection to New Types via Neural Networks
Thien Huu Nguyen, Lisheng Fu, Kyunghyun Cho and Ralph Grishman
Proceedings of ACL Workshop on Representation Learning for NLP, Berlin, Germany, 2016
[PAPER]
-
Combining Neural Networks and Log-linear Models to Improve Relation Extraction
Thien Huu Nguyen and Ralph Grishman
Proceedings of IJCAI Workshop on Deep Learning for Artificial Intelligence, New York, USA, 2016
[PAPER][CODE]
-
Toward Mention Detection Robustness with Recurrent Neural Networks
Thien Huu Nguyen, Avirup Sil, Georgiana Dinu, and Radu Florian
Proceedings of IJCAI Workshop on Deep Learning for Artificial Intelligence, New York, USA, 2016
[PAPER]
2015
-
Improving Event Detection with Abstract Meaning Representation
Xiang Li, Thien Huu Nguyen, Kai Cao, and Ralph Grishman
Proceedings of ACL-IJCNLP Workshop on Computing News Storylines (CNewS 2015), Beijing, China, July, 2015
[PAPER]
-
Event Detection and Domain Adaptation with Convolutional Neural Networks
Thien Huu Nguyen and Ralph Grishman
Proceedings of ACL-IJCNLP 2015, Beijing, China, July, 2015
[PAPER]
-
Semantic Representations for Domain Adaptation: A Case Study on the Tree Kernel-based Method for Relation Extraction
Thien Huu Nguyen, Barbara Plank and Ralph Grishman
Proceedings of ACL-IJCNLP 2015, Beijing, China, July, 2015
[PAPER][CODE]
-
Relation Extraction: Perspective from Convolutional Neural Networks
Thien Huu Nguyen and Ralph Grishman
Proceedings of NAACL Workshop on Vector Space Modeling for NLP, Denver, Colorado, June, 2015
[PAPER][CODE]
2014
-
New York University 2014 Knowledge Base Population Systems
Thien Huu Nguyen, Yifan He, Maria Pershina, Xiang Li, and Ralph Grishman
Proceedings of Text Analysis Conference (TAC), Gaithersburg, Maryland, USA, November 2014
[PAPER]
-
Employing Word Representations and Regularization for Domain Adaptation of Relation Extraction
Thien Huu Nguyen and Ralph Grishman
Proceedings of ACL 2014, Baltimore, Maryland, USA, June 2014
[PAPER]
2013 and before
-
Combining Proper Name-Coreference with Conditional Random Fields for Semi-supervised Named Entity Recognition in Vietnamese Text
Rathany Chan Sam, Huong Thanh Le, Thuy Thanh Nguyen, and Thien Huu Nguyen
Proceedings of the 15th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Shenzhen, China, May, 2011
[PAPER]
STUDENTS
I am fortunate to work with the following students:
and many other student collaborators.
TEACHING
- CIS 313 - Intermediate Data Structures (W19, W20, W21)
- CIS 607 - Seminar on Deep Learning for Natural Language Processing (W19, W20, S21)
- CIS 472/572 - Machine Learning (S19, S20, S21)
- CIS 410/510 - Natural Language Processing (F19, W21)
PROFESSIONAL SERVICES
- Reviewer: Neural Computation Journal, Transactions on Asian and Low-Resource Language Information Processing, Computational Linguistics
- Program Committee: NAACL (2016, 2018, 2019), COLING (2016, 2018, 2020), ACL (2017, 2018, 2019, 2020), EMNLP (2017, 2018, 2019, 2020), IJCAI (2017), AAAI (2020, 2021), CVPR (2021), NeurIPS (2020), ICLR (2021), AACL (2020), LREC (2018, 2020), Rep4NLP (2017, 2018, 2019, 2020), W-NUT (2019, 2020)
- Area Chair: NAACL (2021), ACL (2021), IJCAI (2021)
- Senior Program Committee: AAAI (2020)
AWARDS
- IBM Ph.D. Fellowship, 2016
- Dean's Dissertation Fellowship, Graduate School of Arts and Science, NYU, 2016-2017
- Harold Grad Prize, Courant Institute of Mathematical Science, NYU, 2016
- Henry MacCracken Fellowship, New York University, 2012 - 2017
- Second Prize in Student Scientific Research Conference, by Ministry of Education and Training, Vietnam, 2012
|
|