Junyi Jessy Li

5 paper cards in Mova's library · 2020–2025

Junyi Jessy Li wrote 5 of the papers Mova reads, in 2020–2025, most of them on Discourse analysis, Dependency parsing; often with Greg Durrett, Yating Wu, Kyle Mahowald.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Is It \textit JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs (2025)
The English discourse particle "just" has several senses: exclusive ("Betsy just eats chicken nuggets"), temporal ("just arrived"), unelaboratory ("Fido is just a dog"), unexplanatory ("the lights just turn on and off") and emphatic ("just delicious").
Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion (2023)
The paper builds the first parser for QUD dependency structures: every sentence after the first gets an anchor sentence earlier in the document and a free-form question, raised by the anchor, that the sentence answers.
Elaborative Simplification as Implicit Questions Under Discussion (2023)
When editors simplify news for children (Newsela), they often add sentences that explain rather than shorten.
QUDeval: The Evaluation of Questions Under Discussion Discourse Parsing (2023)
A QUD dependency parse links each answer sentence to an earlier anchor sentence by an implicit question; evaluating such free-form questions has been manual.
Inquisitive Question Generation for High Level Text Comprehension (2020)
INQUISITIVE is a set of about 19K questions that crowd workers asked while reading the first five sentences of 1,500 news articles one sentence at a time, each question tied to the span it is about and checked not to be answered already by the earlier text.