Yejin Choi

Ideas Mova took (1)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

• kept — Partial-input controls for every course, after the paper's ablation: run the student with the lesson removed (question + options only) and with the question removed (lesson + options only). (Cosmos QA: Machine Reading Comprehension with Contextual… · permanent course controls: no lesson, questions shuffled, key lines removed; all red in all seven courses (biology real 2238/4581, no lesson 1208, shuffled…)

Papers

1. StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements (2024)
   Authorship obfuscation rewrites a text so that its author is hard to identify, while keeping the content and fluency.
2. COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs (2020) measured
   The paper argues that hand-built commonsense knowledge graphs can never cover everything an NLP system will meet.
3. Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning (2019) 1 idea kept
   Cosmos QA has 35,588 four-option questions on 21,886 paragraphs from personal-narrative blogs, written by crowd workers to need commonsense «between the lines»: likely causes of events, what happened before or after, plausible facts about people and things, and counterfactuals («What would have happened if…?»).
4. Abductive Commonsense Reasoning (2019)
   The paper introduces abductive reasoning over narratives. Given two observations O1 and O2, a system must pick the more plausible explanation from two hypotheses (αNLI), or generate one (αNLG). The ART dataset has about 20k contexts taken from ROCStories and over 200k hypotheses, written by crowdworkers and then…
5. Neural AMR: Sequence-to-Sequence Models for Parsing and Generation (2017)
   The paper applies sequence-to-sequence neural models to both AMR parsing and AMR generation. The main obstacle is data sparsity, so the authors pretrain on millions of unlabelled Gigaword sentences: a parser labels them, a generator is pretrained on those pairs, and then both are fine-tuned on the 16,833 gold pairs.…

Co-authors (21)

• Chandra Bhagavatula ×3
• Ronan Le Bras ×3
• Keisuke Sakaguchi ×2
• Antoine Bosselut
• Ari Holtzman
• Chaitanya Malaviya
• Doug Downey
• Hannah Rashkin
• Ioannis Konstas
• Jeff Da
• Jena D. Hwang
• Jillian Fisher
• Lifu Huang
• Luke Zettlemoyer
• Mark Yatskar
• Mitchell L Gordon
• Scott Wen-tau Yih
• Skyler Hallinan
• Srinivasan Iyer
• Ximing Lu
• Zaid Harchaoui

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/yejin-choi/