Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Chenhao Tan

Chenhao Tan

Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making


Jan 27, 2021
Han Liu, Vivian Lai, Chenhao Tan

Figure 1 for Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making
Figure 2 for Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making
Figure 3 for Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making
Figure 4 for Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making
* 42 pages, 22 figures 
  Access Paper or Ask Questions

Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End


Nov 10, 2020
Ramaravind K. Mothilal, Divyat Mahajan, Chenhao Tan, Amit Sharma

Figure 1 for Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
Figure 2 for Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
Figure 3 for Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
Figure 4 for Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
* 14 pages, 9 figures 
  Access Paper or Ask Questions

Evaluating and Characterizing Human Rationales


Oct 09, 2020
Samuel Carton, Anirudh Rathore, Chenhao Tan

Figure 1 for Evaluating and Characterizing Human Rationales
Figure 2 for Evaluating and Characterizing Human Rationales
Figure 3 for Evaluating and Characterizing Human Rationales
Figure 4 for Evaluating and Characterizing Human Rationales
* 14 pages, 15 figures, to appear in EMNLP 2020. Code is available at https://github.com/BoulderDS/evaluating-human-rationales 
  Access Paper or Ask Questions

Characterizing the Value of Information in Medical Notes


Oct 07, 2020
Chao-Chun Hsu, Shantanu Karnwal, Sendhil Mullainathan, Ziad Obermeyer, Chenhao Tan

Figure 1 for Characterizing the Value of Information in Medical Notes
Figure 2 for Characterizing the Value of Information in Medical Notes
Figure 3 for Characterizing the Value of Information in Medical Notes
Figure 4 for Characterizing the Value of Information in Medical Notes
* 15 pages, 12 figures, Findings of EMNLP 2020, code is available at https://github.com/BoulderDS/value-of-medical-notes 
  Access Paper or Ask Questions

Harnessing Explanations to Bridge AI and Humans


Mar 16, 2020
Vivian Lai, Samuel Carton, Chenhao Tan

* 4 pages, CHI 2020 Fair & Responsible AI Workshop 
  Access Paper or Ask Questions

"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans


Jan 14, 2020
Vivian Lai, Han Liu, Chenhao Tan

Figure 1 for "Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans
Figure 2 for "Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans
Figure 3 for "Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans
Figure 4 for "Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans
* 26 pages, 48 figures, CHI 2020 
  Access Paper or Ask Questions

Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers


Dec 06, 2019
Divyat Mahajan, Chenhao Tan, Amit Sharma

Figure 1 for Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
Figure 2 for Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
Figure 3 for Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
Figure 4 for Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
* 2019 NeurIPS Workshop on Do the right thing: Machine learning and Causal Inference for improved decision making 
  Access Paper or Ask Questions

What Gets Echoed? Understanding the "Pointers" in Explanations of Persuasive Arguments


Nov 01, 2019
David Atkinson, Kumar Bhargav Srinivasan, Chenhao Tan

Figure 1 for What Gets Echoed? Understanding the "Pointers" in Explanations of Persuasive Arguments
Figure 2 for What Gets Echoed? Understanding the "Pointers" in Explanations of Persuasive Arguments
Figure 3 for What Gets Echoed? Understanding the "Pointers" in Explanations of Persuasive Arguments
Figure 4 for What Gets Echoed? Understanding the "Pointers" in Explanations of Persuasive Arguments
* 19 pages, 3 figures, EMNLP 2019, the code and dataset are available at https://chenhaot.com/papers/explanation-pointers.html 
  Access Paper or Ask Questions

Content Removal as a Moderation Strategy: Compliance and Other Outcomes in the ChangeMyView Community


Oct 21, 2019
Kumar Bhargav Srinivasan, Cristian Danescu-Niculescu-Mizil, Lillian Lee, Chenhao Tan

Figure 1 for Content Removal as a Moderation Strategy: Compliance and Other Outcomes in the ChangeMyView Community
Figure 2 for Content Removal as a Moderation Strategy: Compliance and Other Outcomes in the ChangeMyView Community
Figure 3 for Content Removal as a Moderation Strategy: Compliance and Other Outcomes in the ChangeMyView Community
Figure 4 for Content Removal as a Moderation Strategy: Compliance and Other Outcomes in the ChangeMyView Community
* 21 pages, 8 figures, accepted at CSCW 2019, the dataset is available at https://chenhaot.com/papers/content-removal.html 
  Access Paper or Ask Questions

Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification


Oct 18, 2019
Vivian Lai, Jon Z. Cai, Chenhao Tan

Figure 1 for Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification
Figure 2 for Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification
Figure 3 for Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification
Figure 4 for Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification
* 17 pages, 18 figures, EMNLP 2019, the code is available at https://vivlai.github.io/ 
  Access Paper or Ask Questions

Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations


May 19, 2019
Ramaravind Kommiya Mothilal, Amit Sharma, Chenhao Tan

Figure 1 for Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
Figure 2 for Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
Figure 3 for Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
Figure 4 for Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
* 11 pages 
  Access Paper or Ask Questions

Learning Fair Representations via an Adversarial Framework


Apr 30, 2019
Rui Feng, Yang Yang, Yuehan Lyu, Chenhao Tan, Yizhou Sun, Chunping Wang

Figure 1 for Learning Fair Representations via an Adversarial Framework
Figure 2 for Learning Fair Representations via an Adversarial Framework
Figure 3 for Learning Fair Representations via an Adversarial Framework
Figure 4 for Learning Fair Representations via an Adversarial Framework

  Access Paper or Ask Questions

No Permanent Friends or Enemies: Tracking Relationships between Nations from News


Apr 18, 2019
Xiaochuang Han, Eunsol Choi, Chenhao Tan

Figure 1 for No Permanent Friends or Enemies: Tracking Relationships between Nations from News
Figure 2 for No Permanent Friends or Enemies: Tracking Relationships between Nations from News
Figure 3 for No Permanent Friends or Enemies: Tracking Relationships between Nations from News
Figure 4 for No Permanent Friends or Enemies: Tracking Relationships between Nations from News
* NAACL 2019; code available at https://github.com/BoulderDS/LARN 
  Access Paper or Ask Questions

Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability


Feb 08, 2019
Brian Lubars, Chenhao Tan

Figure 1 for Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability
Figure 2 for Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability
Figure 3 for Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability
Figure 4 for Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability
* 8 pages, 6 figures, 5 tables, dataset available at https://delegability.github.io 
  Access Paper or Ask Questions

On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection


Nov 28, 2018
Vivian Lai, Chenhao Tan

Figure 1 for On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
Figure 2 for On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
Figure 3 for On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
Figure 4 for On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
* 17 pages, 19 figures, in Proceedings of ACM FAT* 2019, dataset & demo available at https://deception.machineintheloop.com 
  Access Paper or Ask Questions

Neural Models for Documents with Metadata


Oct 23, 2018
Dallas Card, Chenhao Tan, Noah A. Smith

Figure 1 for Neural Models for Documents with Metadata
Figure 2 for Neural Models for Documents with Metadata
Figure 3 for Neural Models for Documents with Metadata
Figure 4 for Neural Models for Documents with Metadata
* Dallas Card, Chenhao Tan, and Noah A. Smith. (2018). Neural Models for Documents with Metadata. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 
 * 13 pages, 3 figures, 6 tables; updating to version published at ACL 2018 
  Access Paper or Ask Questions

LSTMs Exploit Linguistic Attributes of Data


May 29, 2018
Nelson F. Liu, Omer Levy, Roy Schwartz, Chenhao Tan, Noah A. Smith

Figure 1 for LSTMs Exploit Linguistic Attributes of Data
Figure 2 for LSTMs Exploit Linguistic Attributes of Data
Figure 3 for LSTMs Exploit Linguistic Attributes of Data
Figure 4 for LSTMs Exploit Linguistic Attributes of Data
* 7 pages, 4 figures; accepted to ACL 2018 RepL4NLP workshop 
  Access Paper or Ask Questions

"You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debates


Feb 23, 2018
Chenhao Tan, Hao Peng, Noah A. Smith

Figure 1 for "You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debates
Figure 2 for "You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debates
Figure 3 for "You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debates
Figure 4 for "You are no Jack Kennedy": On Media Selection of Highlights from Presidential Debates
* 10 pages, 5 figures, to appear in Proceedings of WWW 2018, data and more at https://chenhaot.com/papers/debate-quotes.html 
  Access Paper or Ask Questions

Dynamic Entity Representations in Neural Language Models


Aug 02, 2017
Yangfeng Ji, Chenhao Tan, Sebastian Martschat, Yejin Choi, Noah A. Smith

Figure 1 for Dynamic Entity Representations in Neural Language Models
Figure 2 for Dynamic Entity Representations in Neural Language Models
Figure 3 for Dynamic Entity Representations in Neural Language Models
Figure 4 for Dynamic Entity Representations in Neural Language Models
* EMNLP 2017 camera-ready version 
  Access Paper or Ask Questions

Friendships, Rivalries, and Trysts: Characterizing Relations between Ideas in Texts


Jul 16, 2017
Chenhao Tan, Dallas Card, Noah A. Smith

Figure 1 for Friendships, Rivalries, and Trysts: Characterizing Relations between Ideas in Texts
Figure 2 for Friendships, Rivalries, and Trysts: Characterizing Relations between Ideas in Texts
Figure 3 for Friendships, Rivalries, and Trysts: Characterizing Relations between Ideas in Texts
Figure 4 for Friendships, Rivalries, and Trysts: Characterizing Relations between Ideas in Texts
* 11 pages, 9 figures, to appear in Proceedings of ACL 2017, code and data available at https://chenhaot.com/pages/idea-relations.html (fixed a typo) 
  Access Paper or Ask Questions

Talk it up or play it down? (Un)expected correlations between (de-)emphasis and recurrence of discussion points in consequential U.S. economic policy meetings


Dec 19, 2016
Chenhao Tan, Lillian Lee

Figure 1 for Talk it up or play it down? (Un)expected correlations between (de-)emphasis and recurrence of discussion points in consequential U.S. economic policy meetings
Figure 2 for Talk it up or play it down? (Un)expected correlations between (de-)emphasis and recurrence of discussion points in consequential U.S. economic policy meetings
Figure 3 for Talk it up or play it down? (Un)expected correlations between (de-)emphasis and recurrence of discussion points in consequential U.S. economic policy meetings
Figure 4 for Talk it up or play it down? (Un)expected correlations between (de-)emphasis and recurrence of discussion points in consequential U.S. economic policy meetings
* 14 pages, 18 figures, presented at Text as Data 2016, data and more at https://chenhaot.com/pages/de-emphasis-fomc.html 
  Access Paper or Ask Questions

Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions


Feb 06, 2016
Chenhao Tan, Vlad Niculae, Cristian Danescu-Niculescu-Mizil, Lillian Lee

Figure 1 for Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions
Figure 2 for Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions
Figure 3 for Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions
Figure 4 for Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions
* 12 pages, 10 figures, to appear in Proceedings of WWW 2016, data and more at https://chenhaot.com/pages/changemyview.html (v2 made a minor correction on submission rules in ChangeMyView.) 
  Access Paper or Ask Questions

All Who Wander: On the Prevalence and Characteristics of Multi-community Engagement


Mar 16, 2015
Chenhao Tan, Lillian Lee

Figure 1 for All Who Wander: On the Prevalence and Characteristics of Multi-community Engagement
Figure 2 for All Who Wander: On the Prevalence and Characteristics of Multi-community Engagement
Figure 3 for All Who Wander: On the Prevalence and Characteristics of Multi-community Engagement
Figure 4 for All Who Wander: On the Prevalence and Characteristics of Multi-community Engagement
* 11 pages, data available at https://chenhaot.com/pages/multi-community.html, Proceedings of WWW 2015 (updated references) 
  Access Paper or Ask Questions

A Corpus of Sentence-level Revisions in Academic Writing: A Step towards Understanding Statement Strength in Communication


May 31, 2014
Chenhao Tan, Lillian Lee

Figure 1 for A Corpus of Sentence-level Revisions in Academic Writing: A Step towards Understanding Statement Strength in Communication
Figure 2 for A Corpus of Sentence-level Revisions in Academic Writing: A Step towards Understanding Statement Strength in Communication
Figure 3 for A Corpus of Sentence-level Revisions in Academic Writing: A Step towards Understanding Statement Strength in Communication
Figure 4 for A Corpus of Sentence-level Revisions in Academic Writing: A Step towards Understanding Statement Strength in Communication
* 6 pages, to appear in Proceedings of ACL 2014 (short paper) 
  Access Paper or Ask Questions

The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter


May 06, 2014
Chenhao Tan, Lillian Lee, Bo Pang

Figure 1 for The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter
Figure 2 for The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter
Figure 3 for The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter
Figure 4 for The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter
* 11 pages, to appear in Proceedings of ACL 2014 
  Access Paper or Ask Questions

Hedge detection as a lens on framing in the GMO debates: A position paper


Jun 05, 2012
Eunsol Choi, Chenhao Tan, Lillian Lee, Cristian Danescu-Niculescu-Mizil, Jennifer Spindel

Figure 1 for Hedge detection as a lens on framing in the GMO debates: A position paper
Figure 2 for Hedge detection as a lens on framing in the GMO debates: A position paper
Figure 3 for Hedge detection as a lens on framing in the GMO debates: A position paper
Figure 4 for Hedge detection as a lens on framing in the GMO debates: A position paper
* 10 pp; to appear in Proceedings of the ACL Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics, 2012. Data available at https://confluence.cornell.edu/display/llresearch/HedgingFramingGMOs 
  Access Paper or Ask Questions

User-level sentiment analysis incorporating social networks


Sep 27, 2011
Chenhao Tan, Lillian Lee, Jie Tang, Long Jiang, Ming Zhou, Ping Li

Figure 1 for User-level sentiment analysis incorporating social networks
Figure 2 for User-level sentiment analysis incorporating social networks
Figure 3 for User-level sentiment analysis incorporating social networks
Figure 4 for User-level sentiment analysis incorporating social networks
* Proceedings of KDD 2011. Poster 
  Access Paper or Ask Questions