Sherry Tongshuang Wu Download PDF

HCII, School of Computer Science Carnegie Mellon University Hamerschlag Dr Pittsburgh, PA 15213

Academic Experience

2022–
Carnegie Mellon University, Assistant Professor

Human-Computer Interaction Institute (CMU HCII)

Language Technology Institute (CMU LTI)

2016–22
University of Washington, Research Assistant
with Jeffrey Heer, Dan Weld

Pitfalls in status quo human-AI interactions.

Principles and tools for enhanced NLP model analysis.

Controllable generators for model analysis and improvement.

Education

2016–22
Ph.D. in Computer Science and Engineering
University of Washington, Seattle, WA
Thesis: Interactive AI Model Debugging and Correction
Advisor: Jeffrey Heer, Dan Weld
Committee: Marco Tulio Ribeiro, Noah Smith, Mari Ostendorf
2016–18
M.S. in Computer Science and Engineering
University of Washington, Seattle, WA
2012–16
B.Eng. in Computer Science and Engineering
Hong Kong University of Science and Technology, Hong Kong, Hong Kong
Advisor: Huamin Qu
2014
Exchange student in Computer Science and Engineering
University of Michigan, Ann Arbor, MI

Industry Experience

2021
Google Brain/PAIR, Research Intern & Part-time Student Researcher
with Carrie Cai, Michael Terry

Transparent & controllable human-AI collaborations via multi-step problem-solving.

2019
Microsoft Research, Research Intern
with Marco Tulio Ribeiro

Behavioral testing for NLP models covering broad model capabilities.

2018–19
Apple Inc., Full-time Intern & Part-time Intern
with Chris DuBois, Kayur Patel, Kanit Wongsuphasawat, Donghao Ren, Charlie Maalouf

Structural analysis for unstructured text datasets.

2017
Microsoft Research, Research Intern
with Bongshin Lee, Ece Kamar, Saleema Amersh

Uncertainty-aware data labeling and visual refinement.

2015
Microsoft Research Asia, Research Intern
with Weiwei Cui

De-cluttering statistical graphs.

Publications

* denotes equal contribution

Manuscripts and Pre-prints

2021
P.1
Kaustubh D Dhole, Varun Gangal, Sebastian Gehrmann, Aadesh Gupta, Zhenhao Li, Saad Mahamood, Abinaya Mahendiran, Simon Mille, Ashish Srivastava, Samson Tan, Tongshuang Wu, Jascha Sohl-Dickstein, Jinho D Choi, Eduard Hovy, Ondrej Dusek, Sebastian Ruder, et al.. NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation . In arXiv:2112.02721.
arXiv 2021

Peer-reviewed Conference and Journal Publications

2022
P.2
Ying Xu, Dakuo Wang, Mo Yu, Daniel Ritchie, Bingsheng Yao, Tongshuang Wu, Zheng Zheng, Toby Jia-Jun Li, Nora Bradford, Branda Sun, Tran Bao Hoang, Yisi Sang, Yufang Hou, Xiaojuan Ma, Diyi Yang, Nanyun Peng, Zhou Yu, Mark Warschauer. Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension . In the 60th Annual Meeting of the Association for Computational Linguistics.
ACL 2022
P.3
Hua Shen, Tongshuang Wu, Wenbo Guo, Daniel Ritchie, Ting-Hao 'Kenneth' Huang. Are Shortest Rationales the Best Explanations for Human Understanding? . In the 60th Annual Meeting of the Association for Computational Linguistics.
ACL 2022
P.4
Bingsheng Yao, Dakuo Wang, Tongshuang Wu, Toby Jia-Jun Li, Mo Yu, Ying Xu. It is AI's Turn to Ask Humans a Question: Question and Answer Pair Generation for Children Storybooks with FairytaleQA Dataset . In the 60th Annual Meeting of the Association for Computational Linguistics.
ACL 2022
P.5
Tongshuang Wu*, Alexis Ross*, Hao Peng, Matthew E. Peters, Matt Gardner. Tailor: Generating and Perturbing Text with Semantic Controls . In the 60th Annual Meeting of the Association for Computational Linguistics.
ACL 2022
P.6
Jiao Sun, Tongshuang Wu, Yue Jiang, Ronil Awalegaonkar, Xi Victoria Lin, Diyi Yang. Pretty Princess vs. Successful Leader: Gender Roles in Greeting Card Messages . In the 2022 Conference on Human Factors in Computing Systems.
CHI 2022
P.7
Zheng Zhang, Ying Xu, Bingsheng Yao, Daniel Ritchie, Tongshuang Wu, Mo Yu, Dakuo Wang, Toby Jia-Jun Li. StoryBuddy: A Human-AI Collaborative Agent for Parent-Child Interactive Storytelling with Flexible Parent Involvement . In the 2022 Conference on Human Factors in Computing Systems.
CHI 2022
P.8
Tongshuang Wu, Michael Terry, Carrie J. Cai. AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts . In the 2022 Conference on Human Factors in Computing Systems.
CHI 2022
2021
P.9
Tongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer, Daniel S. Weld. Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models . In the 59th Annual Meeting of the Association for Computational Linguistics.
ACL 2021
P.10
Tongshuang Wu*, Gagan Bansal*, Joyce Zhou+, Raymond Fok+, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, Daniel S. Weld. Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance . In the 2021 Conference on Human Factors in Computing Systems.
CHI 2021
P.11
Xingbo Wang, Yao Ming, Tongshuang Wu, Haipeng Zeng, Yong Wang, Huamin Qu. DeHumor: Visual Analytics forDecomposing Humor . In IEEE Transactions on Visualization and Computer Graphics.
TVCG 2021
2020
P.12
Marco Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin, Sameer Singh. Beyond Accuracy: Behavioral Testing of NLP Models with CheckList . In the 58th Annual Meeting of the Association for Computational Linguistics.
ACL 2020 Best Paper
P.13
Alison Smith-Renner, Ron Fan, Melissa Birchfield, Tongshuang Wu, Jordan Boyd-Graber, Daniel S. Weld, Leah Findlater. No Explainability without Accountability: An Empirical Study of Explanations and Feedback in Interactive ML . In the 2020 Conference on Human Factors in Computing Systems.
CHI 2020
P.14
Tongshuang Wu, Kanit (Ham) Wongsuphasawat, Donghao Ren, Kayur Patel, Chris DuBois. Tempura: Query Analysis with Structural Templates . In the 2020 Conference on Human Factors in Computing Systems.
CHI 2020
P.15
Tongshuang Wu*, Zhihang Dong*, Sicheng Song, Mingrui Zhang. Interactive Attention Model Explorer for Natural Language Processing Tasks with Unbalanced Data Sizes . In IEEE Pacific Visualization Symposium 2020.
PacificVis 2020
2019
P.16
Tongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer, Daniel S. Weld. Errudite: Scalable, Reproducible, and Testable Error Analysis . In the 57th Annual Meeting of the Association for Computational Linguistics.
ACL 2019
P.17
Yang Shi, Maoran Xu, Rongwen Zhao, Hao Fu, Tongshuang Wu, Nan Cao. Interactive Context-Aware Anomaly Detection Guided by User Feedback . In IEEE Transactions on Human-Machine Systems.
THMS 2019
P.18
Tongshuang Wu, Daniel S. Weld, Jeffrey Heer. Local Decision Pitfalls in Interactive Machine Learning: An Investigation into Feature Selection in Sentiment Analysis . In ACM Transactions on Computer-Human Interaction 26.4.
TOCHI 2019
2016
P.19
Tongshuang Wu, Yuan Yao, Yuqing Duan, Xinzhi Fan, Huamin Qu. NetworkSeer: Visual Analysis for Social Network in MOOCs . In IEEE Pacific Visualization Symposium 2016.
PacificVis 2016 Best Paper
P.20
Yun Wang, Tongshuang Wu, Zhutian Chen, Huamin Qu, Qiong Luo. STAC: Enhancing Stacked Graphs for Time Series Analysis . In IEEE Pacific Visualization Symposium 2016.
PacificVis 2016
P.21
Tongshuang Wu, Yingcai Wu, Conglei Shi, Huamin Qu, Weiwei Cui. PieceStack: Toward Better Understanding of Stacked Graphs . In IEEE Transactions on Visualization and Computer Graphics (Proc. PacificVis 2016).
TVCG 2016 Honorable Mention
P.22
Qiaomu Shen, Tongshuang Wu, Haiyan Yang, Yanhong Wu, Huamin Qu, Weiwei Cui. NameClarifier: A Visual Analytics System for Author Name Disambiguation . In IEEE Transactions on Visualization and Computer Graphics (Proc. VAST 2016).
TVCG 2016

Posters, Extended Abstracts, Workshop Papers and Technical Reports

2022
W.1
Zheng Zheng, Ying Xu, Yanhao Wang, Tongshuang Wu, Bingsheng Yao, Daniel Ritchie, Mo Yu, Dakuo Wang, Toby Jia-Jun Li. Building a storytelling conversational agent through parent-AI collaboration . In AAAI Artificial Intelligence for Education Workshop.
AAAI 2022
W.2
Tongshuang Wu*, Ellen Jiang*, Aaron Donsbach, Jeff Gray, Alejandra Molina, Michael Terry, Carrie J. Cai. PromptChainer: Chaining Large Language Model Promptsthrough Visual Programming . In the 2022 Conference on Human Factors in Computing Systems (Late Breaking Work).
CHI LBW 2022
2021
2018
W.4
Halden Lin, Tongshuang Wu, Kanit (Ham) Wongsuphasawat, Yejin Choi, Jeffrey Heer. Visualizing Attention in Sequence-to-Sequence Summarization Models . In IEEE Conference on Visual Analytics Science and Technology.
VAST 2018

Patent

2022
PT.1
Ajit Narayanan, Subhashini Venugopalan, Tongshuang Wu, Shanqing Cai, Michael Terry, Meredith Morris, Carrie Cai. Providing Suggestions of Expanded Text from Abbreviated Text Input.
US Patent (Defensive Publication) 2022
PT.2
Carrie Cai, Tongshuang Wu, Michael Terry. Transparent and Controllable Human-AI Interaction via Chaining of Machine-Learned Language Models.
US Patent US63/251,264 (submitted), 2021 2022

SELECTED HONORS AND AWARDS

2022
CHI 2022 Honorable Mention Award
2020
Rising Stars in EECS Workshop (UC Berkeley)
A highly selective workshop based on academic excellence and commitment to advancing equity and inclusion.
2020
ACL 2020 Best Paper Award
2016–17
Faithful Steward Endowed Fellowship in Computer Science & Engineering
2012–16
Scholarship Scheme for Continuing Undergraduate Students
2016
IEEE PacificVis 2016 Honorable Mention Award
2016
IEEE PacificVis 2016 Best Notes Paper

Teaching Experience

Teaching Assistant

2019
CSE 512 Data Visualization, University of Washingon
Graduate level course, 112 students (Instructor: Jeffrey Heer)
2018
CSE 442 Data Visualization, University of Washingon
Undergraduate level course, 109 students (Instructor: Jeffrey Heer)

Guest Lecture

2021
HCI+AI Interaction, University of Notre Dame
In CSE 60427: Human-Centered Computing Research
2019
Model Interpretability, University of Washington
In CSE 512: Data Visualization

Mentoring Experience

Prior to CMU

2021
Sebastin Santy (Junior PhD student at the University of Washington)
The design and creation of an HCI+NLP research playbook.
Yi Guo (Junior PhD student at Tongji University)
Co-supervised with Nan Cao. Natural-language-based visualization generation.
2019
Jiao Sun (PhD student at the University of Southern California)
Co-supervised with Diyi Yang. Gender bias in NLP datasets.
Joyce Zhou (UW CSE'20 Master's student, now a PhD student at Cornell University)
Co-supervised with Dan Weld & Gagan Bansal. Human-AI teaming.
2018
Akshat Shrivastava (UW CSE'19 Master's student, now at Facebook)
Active learning for sequence labeling.
Halden Lin (UW CSE'19 Master's student, now at Apple Inc.)
Attention visualization for NLP models.

Invited Talks

2022
Peking University, Wangxuan Institute of Computer Technology (2022.3)
DADC: Dynamic Adversarial Data Collection, NAACL 2022 (2022.7)
MIT Computer Science & Artificial Intelligence Laboratory (2022.3)
Stanford University, Computer Science Department (2022.3)
Princeton University, Computer Science Department (2022.3)
Cornell University, Computer Science Department (2022.3)
Carnegie Mellon University, Human-Computer Interaction Institute (2022.3)
Peking University, Wangxuan Institute of Computer Technology (2022.3)
UT Austin, Computer Science Department (2022.2)
University of Chicago, Data Science Institute (2022.2)
Hong kong University of Science and Technology, Computer Science Department (2022.2)
2021
Google Research (2021.7)
ACM CHI Doctoral Consortium (2021.5)
Interactive Data Exploration System (IDEAS) lab, Shandong University (2021.4)
Transparent and Controllable Collaboration with Large Language Models
Google Film Sprint: Fluid Language Integrating Muse (2021.1)
Google PAIR: People+AI Research Initiative (2021.7)
University of Notre Dame, Human-Centered Computing Research (2021.1)
Hong Kong University of Science and Technology, VisLab (2021.1)
Machines in the Loop: Explainability, Transparency, and Rich Interaction
ACL InterNLP 2021, invited panelist (2021.8)
Generating and Perturbing Text with Semantic Controls
Allen Institute for Artificial Intelligence, All-AI2 Meeting (2021.8)
2020
Behavioral Testing of NLP Models
AI Technology Review (2020.8)
AI Time PhD (2020.7)
UCLA, Center for Vision, Cognition, Learning and Autonomy (VCLA) (2020.7)
2019
Scalable, Reproducible, and Testable Error Analysis
UW CSE 512, as guest lecturer (2019.5)
Allen Institute for Artificial Intelligence, All-AI2 Meeting (2019.5)
Apple Inc., Knowledge Graph Team Seminar (2019.3)
Robust AI Event: Research & Reality (2019.5)

Professional Service

Organizing Committees

2022
2022
2022
NL-Augmenter (part of GEM: Workshop for Generation, Evaluation, Metrics, ACL 2021)

Program Committees

AI
AAAI HCOMP 2022, ACM FAccT 2022, AAAI 2022, NeurIPS XAI 2021
HCI
IUI TExSS 2022, ACM IUI 2022-23, CHI HCXAI

Paper Reviewing

HCI
ACM CHI 2019-22, TOCHI 2021, UIST 2018/20/22, IUI 2020, CSCW 2020, TiiS 2022
Special recognition for outstanding reviews ACM CHI, IUI
NLP
ACL 2020, EACL 2021, NAACL 2021
AI
NeurIPS 2022, AAAI 2022, AKBC 2021, ACM Computing Surveys 2021
Viz.
IEEE VIS 2017-21, TVCG 2021, EuroVis 2021, PacificVis 2018/20, ChinaVis 2017-19

Community Service

2021
Course design mentor, UW AVELA (A Vision for Electronic Literacy & Access)
Mentored undergraduate students to develop curriculum for high-school web development courses.
Co-organizer, UW Allen School Pre-Application Mentoring Service (PAMS)
A program supporting 107 potential CS PhD applicants, with 80% from underrepresented communities.
Co-organizer, UW Allen School Women's Research Day
An outreach event to women and nonbinary people in research.
Coordinator, UW Allen School Diverse Genders in Research Events
2020
Student contributor, UW Allen School Strategic Plan for Diversity, Equity & Inclusion
Subcomittee Student Assistant, ACM SIGCHI 2021
Student volunteer, IEEE VIS 2020
2019
Reviewer, UW Allen School Graduate Admission Committee
2018
Co-leader, UW Interactive Systems Seminar
2013
Community tutor, HKUST Connect

Media Coverage

2020
2019