Luke Gessler

4 paper cards in Mova's library · 2019–2025

Luke Gessler wrote 4 of the papers Mova reads, in 2019–2025, most of them on Discourse analysis, Part-of-speech tagging; often with Amir Zeldes, Siyao Peng, Shabnam Behzad.

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

Papers

eRST: A Signaled Graph Theory of Discourse Relations and Organization (2025)
Enhanced RST keeps the RST tree (projective, nucleus/satellite, one label per edge, over elementary discourse units) and adds two things.
GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluation (2023)
GENTLE is a small English challenge corpus of about 17k tokens in eight unusual genres: dictionary entries, esports commentary, legal documents, medical notes, poetry, mathematical proofs, syllabuses and threat letters.
AMALGUM – A Free, Balanced, Multilayer English Web Corpus (2020)
AMALGUM is an English web corpus of about 4 million tokens, built from openly licensed online sources in eight genres (news, interviews, travel guides, how-to guides, academic papers, fiction, biographies and forum posts), with about 500k tokens per genre.
A Discourse Signal Annotation System for RST Trees (2019)
The paper extends rstWeb, a browser tool for building Rhetorical Structure Theory trees, so that each relation in the tree can carry the signals that let a reader recognise it.