Refereed Publications

2024

• Artificial Intelligence for the Prediction, Prevention, and Management of Cardiovascular Disease in Women: A Systematic Review

  Rushali Gandhi, Chetan Shirvankar, Ting Wang, Genevieve Gore, Josep Iglesies-Grau, Hervé Tchala Vignon Zomahoun, Jackie Chi Kit Cheung and Samira Abbasgholizadeh Rahimi

  CMDO AI-Health Symposium 2024

  Best Poster Award

• Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset

  Khaoula ChehbouniI, Jonathan Colaço Carr, Yash More, Jackie Chi Kit Cheung and Golnoosh Farnadi

  AFME Workshop 2024

• Do LLMs Build World Representations? Probing Through the Lens of State Abstraction

  Zichao Li, Yanshuai Cao and Jackie Chi Kit Cheung

  NeurIPS 2024

• When is an Embedding Model More Promising than Another?

  Maxime Darrin, Philippe Formont, Ismail Ben Ayed, Jackie Chi Kit Cheung and Pablo Piantanida

  NeurIPS 2024

• Solving the Challenge Set without Solving the Task: On Winograd Schemas as a Test of Pronominal Coreference Resolution

  Ian Porada and Jackie Chi Kit Cheung

  CoNLL 2024

• CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling

  Yu Bai, Xiyuan Zou, Heyan Huang, Sanxing Chen, Marc-Antoine Rondeau, Yang Gao and Jackie Chi Kit Cheung

  EMNLP 2024

• Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations

  Lei Yu, Meng Cao, Jackie Chi Kit Cheung and Yue Dong

  Findings of EMNLP 2024

• Machine-learning-assisted preoperative prediction of pediatric appendicitis severity

  Aylin Erman, Julia Ferreira, Waseem Ab-Ashour, Elena Guadagno, Etienne St-Louis, Jackie Chi Kit Cheung, Sherif Emil and Dan Poenaru

  American Academy of Pediatrics National Conference and Exhibition (AAP 2024)

• GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews

  Maxime Darrin, Ines Arous, Pablo Piantanida and Jackie Chi Kit Cheung

  ACL 2024

• COSMIC: Mutual Information for Task-Agnostic Summarization Evaluation

  Maxime Darrin, Philippe Formont, Jackie Chi Kit Cheung and Pablo Piantanida

  ACL 2024

• ECBD: Evidence-Centered Benchmark Design for NLP

  Yu Lu Liu, Su Lin Blodgett, Jackie Chi Kit Cheung, Vera Liao, Alexandra Olteanu and Ziang Xiao

  ACL 2024

• From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards

  Khaoula Chehbouni, Megha Roshan, Emmanuel Ma, Futian Andrew Wei, Afaf Taik, Jackie Chi Kit Cheung and Golnoosh Farnadi

  Findings of ACL 2024

• Challenges to Evaluating the Generalization of Coreference Resolution Models: A Measurement Modeling Perspective

  Ian Porada, Alexandra Olteanu, Kaheer Suleman, Adam Trischler and Jackie Chi Kit Cheung

  Findings of ACL 2024

• Separately Parameterizing Singleton Detection Improves End-to-end Neural Coreference Resolution

  Xiyuan Zou, Yiran Li, Ian Porada and Jackie Chi Kit Cheung

  NAACL 2024 (Short paper)

• Successor Features for Efficient Multi-Subject Controlled Text Generation

  Meng Cao, Mehdi Fatemi, Jackie Chi Kit Cheung and Samira Shabanian

  ICML 2024

• Performance of ChatGPT in Certification Examination of College of Family Physicians of Canada

  Mehdi Mousavi, Shabnam Shafiee, Jason Harley, Jackie Chi Kit Cheung and Samira Abbasgholizadeh Rahimi

  Family Medicine and Community Health

• A Controlled Reevaluation of Coreference Resolution Models

  Ian Porada, Xiyuan Zou and Jackie Chi Kit Cheung

  LREC-COLING 2024

• Ensemble Distillation for Unsupervised Constituency Parsing

  Behzad Shayegh, Yanshuai Cao, Xiaodan Zhu, Jackie Chi Kit Cheung and Lili Mou

  ICLR 2024

• How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes

  Sabina Elkins, Ekaterina Kochmar, Jackie Chi Kit Cheung and Iulian Vlad Serban

  EAAI 2024

• Unsupervised Layer-wise Score Aggregation for Textual OOD Detection

  Maxime Darrin, Guillaume Staerman, Eduardo Dadalto Camara Gomes, Jackie Chi Kit Cheung, Pablo Piantanida and Pierre Colombo

  AAAI 2024

2023

• Investigating the Effect of Pre-finetuning BERT Models on NLI Involving Presuppositions

  Jad Kabbara and Jackie Chi Kit Cheung

  Findings of EMNLP 2023

• Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness

  Zichao Li, Ines Arous, Siva Reddy and Jackie Chi Kit Cheung

  Findings of EMNLP 2023

• Responsible AI Considerations in Text Summarization Research: A Review of Current Practices

  Yu Lu Liu, Meng Cao, Su Lin Blodgett, Jackie Chi Kit Cheung, Alexandra Olteanu and Adam Trischler

  Findings of EMNLP 2023

• BALAUR: Language Model Pretraining with Lexical Semantic Relations

  Andrei Mircea and Jackie Chi Kit Cheung

  Findings of EMNLP 2023

• Qualitative Code Suggestion: A Human-Centric Approach To Qualitative Coding

  Cesare Spinoso-Di Piano, Samira Abbasgholizadeh Rahimi and Jackie Chi Kit Cheung

  Findings of EMNLP 2023

• Systematic Generalization by Finetuning? Analyzing Pretrained Language Models Using Constituency Tests

  Aishik Chakraborty, Jackie Chi Kit Cheung and Timothy J. O’ Donnell

  BlackBoxNLP 2023

  Honourable Mention for Best Paper

• McGill BabyLM Shared Task Submission: The Effects of Data Formatting and Structural Biases

  Ziling Cheng, Rahul Aralikatte, Ian Porada, Cesare Spinoso-Di Piano and Jackie Chi Kit Cheung

  BabyLM Shared Task of CoNLL 2023

• Analyzing Multi-Sentence Aggregation in Abstractive Summarization via the Shapley Value

  Jingyi He, Meng Cao and Jackie Chi Kit Cheung

  NewSum 2023

• McGill at CRAC 2023: Multilingual Generalization of Entity-Ranking Coreference Resolution Models

  Ian Porada and Jackie Chi Kit Cheung

  CRAC-MCR 2023

• The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources

  Akshatha Arodi, Martin Pömsl, Kaheer Suleman, Adam Trischler, Alexandra Olteanu and Jackie Chi Kit Cheung

  ACL 2023

  Best Paper Nominee

• Varta: A Large-Scale Headline-Generation Dataset for Indic Languages

  Rahul Aralikatte, Ziling Cheng, Sumanth Doddapaneni and Jackie Chi Kit Cheung

  Findings of ACL 2023

• How Useful are Educational Questions Generated by Large Language Models?

  Sabina Elkins, Ekaterina Kochmar, Iulian Serban, and Jackie Chi Kit Cheung

  AIED 2023 Late-Breaking Results

• Systematic Rectification of Language Models via Dead-end Analysis

  Meng Cao, Mehdi Fatemi, Jackie Chi Kit Cheung and Samira Shabanian

  ICLR 2023

2022

• A Multifaceted Framework to Evaluate Evasion, Content Preservation, and Mis-attribution in Authorship Obfuscation Techniques

  Malik Altakrori, Thomas Scialom, Benjamin C. M. Fung and Jackie Chi Kit Cheung

  EMNLP 2022

• Learning with Rejection for Abstractive Text Summarization

  Meng Cao, Yue Dong, Jingyi He and Jackie Chi Kit Cheung

  EMNLP 2022

• Source-summary Entity Aggregation in Abstractive Summarization

  José-Ángel González, Annie Louis and Jackie Chi Kit Cheung

  COLING 2022

• Investigating the Performance of Transformer-Based NLI Models on Presuppositional Inferences

  Jad Kabbara and Jackie Chi Kit Cheung

  COLING 2022 (Short paper)

  Best Short Paper Award

• Question Personalization in an Intelligent Tutoring System

  Sabina Elkins, Robert Belfer, Ekaterina Kochmar, Iulian Serban and Jackie Chi Kit Cheung

  AIED 2022 Late-Breaking Results

  arXiv preprint

• Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge

  Ian Porada, Alessandro Sordoni and Jackie Chi Kit Cheung

  NAACL 2022 (Short paper)

• Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

  Meng Cao, Yue Dong and Jackie Chi Kit Cheung

  ACL 2022

• Characterizing Idioms: Conventionality and Contingency

  Michaela Socolof, Jackie Chi Kit Cheung, Michael Wagner and Timothy J. O'Donnell

  ACL 2022

• Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation

  Kushal Arora, Layla El Asri, Hareesh Bahuleyan and Jackie Chi Kit Cheung

  Findings of ACL 2022

• Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment

  Zichao Li, Prakhar Sharma, Xing Han Lu, Jackie Chi Kit Cheung and Siva Reddy

  Findings of ACL 2022

2021

• Textual Time Travel: A Temporally Informed Approach to Theory of Mind

  Akshatha Arodi, Jackie Chi Kit Cheung

  Findings of EMNLP 2021

• The Topic Confusion Task: A Novel Evaluation Scenario for Authorship Attribution

  Malik Altakrori, Jackie Chi Kit Cheung and Benjamin C. M. Fung

  Findings of EMNLP 2021

• Post-Editing Extractive Summaries by Definiteness Prediction

  Jad Kabbara and Jackie Chi Kit Cheung

  Findings of EMNLP 2021

• ADEPT: An Adjective-Dependent Plausibility Task

  Ali Emami, Ian Porada, Alexandra Olteanu, Kaheer Suleman, Adam Trischler and Jackie Chi Kit Cheung

  ACL-IJCNLP 2021

• On-the-Fly Attention Modulation for Neural Generation

  Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, Antoine Bosselut, Jackie Chi Kit Cheung and Yejin Choi

  Findings of ACL 2021

• Optimizing Deeper Transformers on Small Datasets

  Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J.D. Prince and Yanshuai Cao

  ACL-IJCNLP 2021

• TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion

  Jiapeng Wu, Yishi Xu, Yingxue Zhang, Chen Ma, Mark Coates and Jackie Chi Kit Cheung

  SIGIR 2021

• Modeling Event Plausibility with Consistent Conceptual Abstraction

  Ian Porada, Kaheer Suleman, Adam Trischler and Jackie Chi Kit Cheung

  NAACL-HLT 2021

• Discourse-Aware Unsupervised Summarization for Long Scientific Documents

  Yue Dong, Andrei Mircea Romascanu and Jackie Chi Kit Cheung

  EACL 2021

• Deep Discourse Analysis for Generating Personalized Feedback in Intelligent Tutor Systems

  Matt Grenander, Robert Belfer, Ekaterina Kochmar, Iulian Serban, François St-Hilaire and Jackie Chi Kit Cheung

  EAAI-21

2020

• An Analysis of Dataset Overlap on Winograd-Style Tasks

  Ali Emami, Kaheer Suleman, Adam Trischler and Jackie Chi Kit Cheung

  COLING 2020

• Learning Efficient Task-Specific Meta-Embeddings with Word Prisms

  Jingyi He, KC Tsiolis, Kian Kenyon-Dean and Jackie Chi Kit Cheung

  COLING 2020

• On The Systematicity of Probing Contextualized Word Representations

  Abhilasha Ravichander, Eduard Hovy, Kaheer Suleman, Adam Trischler and Jackie Chi Kit Cheung

  *SEM 2020

• Multi-Fact Correction in Abstractive Text Summarization

  Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, Jackie Chi Kit Cheung and Jingjing Liu

  EMNLP 2020

• TESA: A Task in Entity Semantic Aggregation for Abstractive Summarization

  Clément Jumel, Annie Louis and Jackie Chi Kit Cheung

  EMNLP 2020

• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion

  Jiapeng Wu, Meng Cao, Jackie Chi Kit Cheung and William L. Hamilton

  EMNLP 2020

• Factual Error Correction for Abstractive Summarization Models

  Meng Cao, Yue Dong, Jiapeng Wu and Jackie Chi Kit Cheung

  EMNLP 2020 (Short paper)

• Deconstructing word embedding algorithms

  Kian Kenyon-Dean, Edward Newell and Jackie Chi Kit Cheung

  EMNLP 2020 (Short paper)

• On Variational Learning of Controllable Representations for Text without Supervision

  Peng Xu, Jackie Chi Kit Cheung, Yanshuai Cao

  ICML 2020

• Investigating the Influence of Selected Linguistic Features on Authorship Attribution using German News Articles

  Manuel Sage, Pietro Cruciata, Raed Abdo, Jackie Chi Kit Cheung, Yaoyao Fiona Zhao

  SwissText & KONVENS 2020

• Learning Lexical Subspaces in a Distributional Vector Space.

  Kushal Arora, Aishik Chakraborty and Jackie Chi Kit Cheung

  TACL

  Presented at ACL 2020

2019

• Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text

  Ian Porada, Kaheer Suleman, Jackie C.K. Cheung

  Workshop on Commonsense Inference in Natural Language Processing (@ EMNLP-IJCNLP 2019)

• Referring Expression Generation Using Entity Profiles

  Meng Cao and Jackie C.K. Cheung

  EMNLP-IJCNLP 2019

• Countering the Effects of Lead Bias in News Summarization via Multi-stage Training and Auxiliary Losses

  Matt Grenander, Yue Dong, Jackie C.K. Cheung and Annie Louis

  EMNLP-IJCNLP 2019 (Short paper)

• How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG

  Paul Trichelair, Ali Emami, Adam Trischler, Kaheer Suleman and Jackie C.K. Cheung

  EMNLP-IJCNLP 2019 (Short paper)

• EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing

  Yue Dong, Zichao Li, Mehdi Rezagholizadeh and Jackie C.K. Cheung

  ACL 2019

• The KnowRef Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution

  Ali Emami, Paul Trichelair, Adam Trischler, Kaheer Suleman, Hannes Schulz and Jackie C.K. Cheung

  ACL 2019

• A Cross-Domain Transferable Neural Coherence Model

  Peng Xu, Hamidreza Saghir, Jin Sung Kang, Teng Long, Avishek Joey Bose, Yanshuai Cao and Jackie C.K. Cheung

  ACL 2019

• Understanding the Behaviour of Neural Abstractive Summarizers Using Contrastive Examples

  Krtin Kumar and Jackie C.K. Cheung

  NAACL 2019 (Short paper)

• Clustering-Oriented Representation Learning with Attractive-Repulsive Loss

  Kian Kenyon-Dean, Andre Cianflone, Lucas Page-Caccia, Guillaume Rabusseau, Jackie C.K. Cheung, Doina Precup

  AAAI-19 Workshop on Network Interpretability for Deep Learning

• Generating Character Descriptions for Automatic Summarization of Fiction

  Weiwei Zhang, Jackie C.K. Cheung and Joel Oren

  AAAI 2019

• Learning Multi-task Communication with Message Passing for Sequence Learning

  Pengfei Liu, Jie Fu, Yue Dong, Xipeng Qiu and Jackie C.K. Cheung

  AAAI 2019

• Contextualized Non-local Neural Networks for Sequence Learning

  Pengfei Liu, Shuaichen Chang, Jian Tang and Jackie C.K. Cheung

  AAAI 2019

2018

• On the Evaluation of Common-Sense Reasoning in Natural Language Understanding

  Paul Trichelair, Ali Emami, Jackie C.K. Cheung, Adam Trischler, Kaheer Suleman and Fernando Diaz

  NeurIPS 2018 Workshop on Critiquing and Correcting Trends in Machine Learning

  This version is non-archival. See our EMNLP 2019 paper for the archival version with additional results.

• BanditSum: Extractive Summarization as a Contextual Bandit

  Yue Dong, Yikang Shen, Eric Crawford, Herke van Hoof and Jackie C.K. Cheung

  EMNLP 2018

• A Knowledge Hunting Framework for Common Sense Reasoning

  Ali Emami, Adam Trischler, Kaheer Suleman, Noelia de la Cruz and Jackie C.K. Cheung

  EMNLP 2018

• A Hierarchical Neural Attention-based Text Classifier

  Koustuv Sinha, Yue Dong, Jackie C.K. Cheung and Derek Ruths

  EMNLP 2018 (Short paper)

• Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers

  Andre Cianflone, Yulan Feng, Jad Kabbara and Jackie C.K. Cheung

  ACL 2018
  Best Paper Award

• Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization

  Kian Kenyon-Dean, Jackie C.K. Cheung and Doina Precup

  *SEM 2018

• Coarse Lexical Frame Acquisition at the Syntax-Semantics Interface Using a Latent-Variable PCFG Model

  Laura Kallmeyer, Behrang QasemiZadeh and Jackie C.K. Cheung

  *SEM 2018

• A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge

  Ali Emami, Adam Trischler, Kaheer Suleman and Jackie C.K. Cheung

  NAACL 2018 Student Research Workshop
  Outstanding Paper Award
  See our EMNLP 2018 paper above for an extended version.

• Commonsense Mining as Knowledge Base Completion? A Study on the Impact of Novelty

  Stanislaw Jastrzebski, Dzmitry Bahdanau, Seyedarian Hosseini, Michael Noukhovitch, Yoshua Bengio and Jackie C.K. Cheung

  Workshop on New Forms of Generalization in Deep Learning and Natural Language Processing (@ NAACL 2018)

• Constructing a Lexicon of Relational Nouns

  Edward Newell and Jackie C.K. Cheung

  LREC 2018

2017

• World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions

  Teng Long, Emmanuel Bengio, Ryan Lowe, Jackie C.K. Cheung and Doina Precup

  EMNLP 2017

  Wikilinks Rare Entity Prediction Dataset

• Predicting Success in Goal-Driven Human-Human Dialogues

  Michael Noseworthy, Jackie C.K. Cheung, and Joelle Pineau

  SIGDIAL 2017

• Detecting Large Concept Extensions for Conceptual Analysis

  Louis Chartrand, Jackie C.K. Cheung, and Mohamed Bouguessa

  MLDM 2017

• Nifty Assignments

  Nick Parlante, Julie Zelenski, Dave Feinberg, Kunal Mishra, Josh Hug, Kevin Wayne, Michael Guerzhoy, Jackie C.K. Cheung, and François Pitt

  SIGCSE 2017

2016

• Predicting Sentential Semantic Compatibility for Aggregation in Text-to-Text Generation

  Victor Chenal and Jackie C.K. Cheung

  COLING 2016

• Capturing Pragmatic Knowledge in Article Usage Prediction using LSTMs

  Jad Kabbara, Yulan Feng, and Jackie C.K. Cheung

  COLING 2016

• Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks

  Jad Kabbara and Jackie C.K. Cheung

  Workshop on Uphill Battles in Language Processing: Scaling Early Achievements to Robust Methods (@ EMNLP 2016)

• Accurate Pinyin-English Codeswitched Language Identification

  Meng Xuan Xia and Jackie C.K. Cheung

  Second Workshop on Computational Approaches to Code Switching (@ EMNLP 2016)

• Verb Phrase Ellipsis Resolution Using Discriminative and Margin-Infused Algorithms

  Kian-Kenyon Dean, Jackie C.K. Cheung, and Doina Precup

  EMNLP 2016

• Leveraging Lexical Resources for Learning Entity Embeddings in Multi-Relational Data

  Teng Long, Ryan Lowe, Jackie C.K. Cheung, and Doina Precup

  ACL 2016 (Short paper)

2015

• Indicative Tweet Generation: An Extractive Summarization Problem?

  Priya Sidhaye and Jackie C.K. Cheung

  EMNLP 2015

• Concept Extensions as the Basis for Vector-Space Semantics: Combining Distributional and Ontological Information about Entities

  Jackie C.K. Cheung

  Continuous Vector Space Models and their Compositionality (CVSC) 2015

  Parameter settings and data set of Freebase IDs

2008 – 2014

• Unsupervised Sentence Enhancement for Automatic Summarization

  Jackie C.K. Cheung and Gerald Penn

  EMNLP 2014

  ILP details

• Probabilistic Domain Modelling With Contextualized Distributional Semantic Vectors

  Jackie C.K. Cheung and Gerald Penn

  ACL 2013

  Hyperparameter settings

• Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain

  Jackie C.K. Cheung and Gerald Penn

  ACL 2013

• Probabilistic Frame Induction

  Jackie C.K. Cheung, Hoifung Poon and Lucy Vanderwende

  NAACL 2013

• Multi-Document Summarization of Evaluative Text

  Giuseppe Carenini, Jackie C.K. Cheung and Adam Pauls

  Computational Intelligence 2013

• Evaluating Distributional Models of Semantics for Syntactically Invariant Inference

  Jackie C.K. Cheung and Gerald Penn

  EACL 2012

  Evaluation code and preprocessed evaluation data

• Unsupervised Detection of Downward-Entailing Operators By Maximizing Classification Certainty

  Jackie C.K. Cheung and Gerald Penn

  EACL 2012

  Expanded list of downward-entailing operator candidates

• Sequence Clustering and Labeling for Unsupervised Query Intent Discovery

  Jackie C.K. Cheung and Xiao Li

  WSDM 2012

• Utilizing Extra-sentential Context for Parsing

  Jackie C.K. Cheung and Gerald Penn

  EMNLP 2010

  Raw between-sentence parallelism statistics

• Entity-Based Local Coherence Modelling Using Topological Fields

  Jackie C.K. Cheung and Gerald Penn

  ACL 2010

• Topological Field Parsing of German

  Jackie C.K. Cheung and Gerald Penn

  ACL-IJCNLP 2009

  Parsing models

• Optimization-Based Content Selection for Opinion Summarization

  Jackie C.K. Cheung, Giuseppe Carenini and Raymond T. Ng

  UCNLG+Sum 2009

• Extractive vs. NLG-based Abstractive Summarization of Evaluative Text: The Effect of Corpus Controversiality

  Giuseppe Carenini and Jackie C.K. Cheung

  INLG 2008

Theses

• Distributional Semantics for Robust Automatic Summarization

  Jackie C.K. Cheung

  Ph.D. dissertation, 2014

  University of Toronto

• Parsing German Topological Fields with Probabilistic Context-Free Grammars

  Jackie C.K. Cheung

  M.Sc. paper, 2010

  University of Toronto

• Comparing Abstractive and Extractive Summarization of Evaluative Text: Controversiality and Content Selection

  Jackie C.K. Cheung

  Undergraduate honours thesis, 2008

  University of British Columbia