🧑‍🔬 Jackie Chi Kit Cheung

Affiliations

• McGill University · Montreal, Canada — current · 2015–2026 on 88 papers
• Mila - Quebec Artificial Intelligence Institute · Montreal, Canada — current · 2018–2026 on 29 papers
• Canadian Institute for Advanced Research · Toronto, Canada — current · 2019–2026 on 16 papers
• Centre Universitaire de Mila · Mila, Algeria — 2019–2023 on 7 papers
• University of Amsterdam · Amsterdam, Netherlands — 2018 on 2 papers
• Université de Montréal · Montreal, Canada — 2018 on 2 papers
• University of Toronto · Toronto, Canada — 2009–2014 on 11 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 11 more institutions on single bylines are not listed.

Topics

Coreference resolution4Implicature2Summarization2Machine translation1Evaluation & benchmarks1Reasoning1

Papers

The most cited first (OpenAlex and our library).

1. EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing (2019 · 241 citations)
   The paper addresses a weakness of sentence simplification systems built on machine translation. These seq2seq models learn simplifying changes only indirectly from complex-simple pairs, so they often copy the input unchanged. The authors propose EditNTS, an end-to-end Neural Programmer-Interpreter model. It works…
2. Factual Error Correction for Abstractive Summarization Models (2020 · 217 citations)
   Abstractive summarizers built on pre-trained transformers often produce summaries that contradict their source documents.
3. Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization (2022 · 167 citations)
   Abstractive summarizers frequently produce content that the source document does not support, and prior work usually treats all such hallucinations as errors.
4. Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization (2018 · 87 citations)
   The paper addresses event coreference resolution: deciding which event mentions, within one document or across several, describe the same real-world event.
5. The KnowRef Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution (2019 · 73 citations)
   KnowRef is a set of 8,724 natural Winograd-like passages: two person noun phrases, then one connective (but, because, although, when, so …), then a pronoun that agrees with both («Paul helped Lionel hide when he was pursued by the authorities»).
6. Verb Phrase Ellipsis Resolution Using Discriminative and Margin-Infused Algorithms (2016 · 24 citations)
   The paper resolves VP ellipsis (VPE) in two steps. The first step decides whether a word triggers VPE. The second picks the antecedent clause and its exact boundaries. Both steps are supervised machine learning over features from an automatically parsed corpus, the Bos and Spenader VPE data on the Wall Street…
7. Investigating the Performance of Transformer-Based NLI Models on Presuppositional Inferences (2022 · 12 citations)
   This paper asks whether transformer models fine-tuned for natural language inference actually reason about presuppositions or simply rely on shallow regularities.
8. Challenges to Evaluating the Generalization of Coreference Resolution Models: A Measurement Modeling Perspective (2024 · 10 citations)
   The paper asks whether multi-dataset evaluations of coreference models really measure generalization. It borrows the measurement-modelling framework of the social sciences: a construct (what is measured, here coreference) is separated from its operationalization (how the annotation guidelines implement it). Seven…
9. Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers (2018 · 10 citations)
   The task is to predict, from the preceding discourse, whether an adverbial presupposition trigger (too, again, also, still, yet) belongs on a given head word.
10. A Controlled Reevaluation of Coreference Resolution Models (2024 · 7 citations)
    Every leading coreference resolution (CR) system finetunes a pretrained language model. Because each paper uses a different backbone and training setup, it is unclear whether reported gains come from new task-specific architectures or simply from stronger language models. The authors reimplemented five CR models…

Also in our library

8 more works of theirs are in our library without a page here yet; they will appear as we publish them.

Co-authors here

12 co-authors with a page, the most papers together first.

• Yue Dong ×3
• Adam Trischler ×2
• Doina Precup ×2
• Ian Porada ×2
• Jad Kabbara ×2
• Kaheer Suleman ×2
• Kian Kenyon-Dean ×2
• Meng Cao ×2
• Ali Emami
• Hannes Schulz
• Mehdi Rezagholizadeh
• Zichao Li

Cited by

Papers of our library cite their works 533 times (of the 140 884 papers whose bibliographies we read); 78 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jackie-chi-kit-cheung/