Welcome to my homepage!

I am a Research Scientist in the Central Applied Science team at Meta, where I develop computational methods and scalable systems to understand latent structures in complex data. My current interests lie in addressing the challenges of uncertainty in both human and LLM-generated labels, which includes advancing methods in data aggregation and crowdsourcing, uncertainty quantification, confidence estimation, and LLM evaluation.

Before joining Meta, I obtained my Ph.D. in Computer Science from the University of Maryland, College Park, where I was co-advised by Prof. Philip Resnik and Prof. Jordan Boyd-Graber. My dissertation research focused on developing probabilistic topic models for applications in natural language processing and computational social science. I received my B.Eng. in Computer Science from Nanyang Technological University (NTU), Singapore.

I grew up in Hanoi, Vietnam. The correct spelling of my name in Vietnamese is Nguyễn Việt An. I usually go by An for short.

Publications (Google Scholar & DBLP)

CalCo: A Hierarchical Bayesian Framework for Scalable Human-LLM Hybrid Labeling
Viet-An Nguyen, Xu Chen, Udi Weinsberg
KDD 2026
[PDF] [OpenReview] [Acceptance rate = ~18.5%]

Efficient Model Performance Evaluation Using a Combination of Expert and Crowd-sourced Labels
Sam Corbett-Davies, Viet-An Nguyen, Udi Weinsberg
AISTATS 2026
[PDF] [OpenReview] [Acceptance rate = 28% (589/2102)]

Efficient Online Crowdsourcing with Complex Annotations
Reshef Meir, Viet-An Nguyen, Xu Chen, Jagdish Ramakrishnan, Udi Weinsberg
AAAI 2024
[PDF] [Full version] [Acceptance rate = 23.75% (2342/9862)]

From Labels to Decisions: A Mapping-Aware Annotator Model
Evan Yao, Jagdish Ramakrishnan, Xu Chen, Viet-An Nguyen, Udi Weinsberg
KDD 2023 (Applied Data Science Track)
[ACM URL] [PDF] [Bibtex] [Acceptance rate = 25% (184/725)]

Crowdsourcing with Contextual Uncertainty
Viet-An Nguyen, Peibei Shi, Jagdish Ramakrishnan, Narjes Torabi, Nimar S. Arora, Udi Weinsberg, Michael Tingley
KDD 2022 (Applied Data Science Track)
Meta Research Blog
[ACM URL] [Meta Research URL] [PDF] [Bibtex] [Oral presentation, Slides] [Acceptance rate = 26% (196/753)]

CLARA: Confidence of Labels and Raters
Viet-An Nguyen, Peibei Shi, Jagdish Ramakrishnan, Udi Weinsberg, Henry C. Lin, Steve Metz, Neil Chandra, Jane Jing, Dimitris Kalimeris
KDD 2020 (Applied Data Science Track)
Meta Research Blog
[ACM URL] [Meta Research URL] [Code] [PDF] [Bibtex] [Oral presentation, Slides] [Acceptance rate = 16% (121/756) (~5.8% for oral presentation)]

Guided Probabilistic Topic Models for Agenda-setting and Framing
Viet-An Nguyen
Ph.D. Dissertation, 2015
[URL] [PDF] [Slides]

Tea Party in the House: A Hierarchical Ideal Point Topic Model and Its Application to Republican Legislators in the 112th Congress
Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik, Kristina Miler
ACL-IJCNLP 2015
[PDF] [Code] [Talk] [Bibtex] [Acceptance rate = 25% (173/692)]

Beyond LDA: Exploring Supervised Topic Modeling for Depression-Related Language in Twitter
Philip Resnik, William Armstrong, Leonardo Claudino, Thang Nguyen, Viet-An Nguyen, and Jordan Boyd-Graber
CLPsych Workshop at NAACL 2015
[PDF] [Bibtex]

Learning a Concept Hierarchy from Multi-labeled Documents
Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik, Jonathan Chang
NIPS 2014
[PDF] [Poster] [Bibtex] [Acceptance rate = 24.7% (414/1678)]

Sometimes Average is Best: The Importance of Averaging for Prediction using MCMC Inference in Topic Modeling
Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik
EMNLP 2014 (short paper)
[PDF] [Poster] [Bibtex] [Acceptance rate = 27.8% (70/252)]

Modeling Topic Control to Detect Influence in Conversations using Nonparametric Topic Models
Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik, Deborah A. Cai, Jennifer E. Midberry, Yuanxin Wang
Machine Learning Journal, 95(3): 381-421, June 2014
[URL] [Manuscript] [Bibtex]

Tree-based Label Dependency Topic Models
Viet-An Nguyen, Jordan Boyd-Graber, Jonathan Chang, Philip Resnik
Topic Models Workshop at NIPS 2013
[PDF] [Poster]

Lexical and Hierarchical Topic Regression
Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik
NIPS 2013
[PDF] [Appendix] [Bibtex] [Poster] [Acceptance rate = 25.4% (360/1420)]

Argviz: Interactive Visualization of Topic Dynamics in Multi-party Conversations
Viet-An Nguyen, Yuening Hu, Jordan Boyd-Graber, Philip Resnik
NAACL-HLT 2013 (demo track)
[PDF] [Poster] [Bibtex]

Dirichlet Mixtures, the Dirichlet Process, and the Structure of Protein Space
Viet-An Nguyen, Jordan Boyd-Graber, Stephen F. Altschul
Journal of Computational Biology, 20(1): 1-18, January 2013
[URL] [Manuscript] [Bibtex]

SITS: A Hierarchical Nonparametric Model using Speaker Identity for Topic Segmentation in Multiparty Conversations
Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik
ACL 2012
[PDF] [Slides] [Bibtex] [Appendix] [Code] [Acceptance rate = 19%]

Visual Analysis of Temporal Trends in Social Networks Using Edge Color Coding and Metric Timelines
Udayan Khurana, Viet-An Nguyen, Hsueh-Chien Cheng, Jae-wook Ahn, Xi (Stephen) Chen, Ben Shneiderman
SocialCom 2011
[URL] [Bibtex] [Technical Report]

Modeling Link Formation Behaviors in Dynamic Social Networks
Viet-An Nguyen, Cane Wing-Ki Leung, Ee-Peng Lim
SBP 2011
[PDF] [URL] [Bibtex]

Detecting Product Review Spammers using Rating Behaviors
Ee-Peng Lim, Viet-An Nguyen, Bing Liu, Nitin Jindal, Hady Wirawan Lauw
CIKM 2010
[PDF] [URL] [Bibtex] [Acceptance rate = 13.4% (127/945)] [Test of Time Award]

Messaging Behavior Modeling in Mobile Social Networks
Byung-Won On, Ee-Peng Lim, Jing Jiang, Freddy Chong Tat Chua, Viet-An Nguyen, Loo-Nin Teow
SIN Workshop at SocialCom 2010
[URL] [Bibtex]

Do You Trust to Get Trust? A Study of Trust Reciprocity Behaviors and Reciprocal Trust Prediction
Viet-An Nguyen, Ee-Peng Lim, Hwee-Hoon Tan, Jing Jiang, Aixin Sun
SDM 2010
[PDF] [Bibtex] [Acceptance rate = 23.4% (82/351)]

To Trust or Not to Trust? Predicting Online Trusts using Trust Antecedent Framework
Viet-An Nguyen, Ee-Peng Lim, Aixin Sun, Jing Jiang, Hwee-Hoon Tan
ICDM 2009
[PDF] [URL] [Slides] [Bibtex] [Acceptance rate = 17.7% (139/786)]

Trust Relationship Prediction Using Online Product Review Data
Nan Ma, Ee-Peng Lim, Viet-An Nguyen, Aixin Sun, Haifeng Liu
CNIKM Workshop at CIKM 2009
[URL] [Slides] [Bibtex]

Rule Evolution Approach for Mining Multivariate Time Series Data
Viet-An Nguyen, Vivekanand Gopalkrishnan
ICEIS 2008
[Bibtex]

Academic Services

  • Area Co-chair: NAACL
  • Conference PC Member / Reviewer: ACL, EMNLP, NAACL, COLING, NeurIPS, ICML, AISTATS, ICLR, EACL, KDD
  • Journal Reviewer: Transactions of the Association for Computational Linguistics, Science Advances, Computer Speech and Language, Machine Learning Journal, Journal of Artificial Intelligence Research