no code implementations • EACL (BEA) 2021 • Goran Glavaš, Ananya Ganesh, Swapna Somasundaran
In this work, we focus on the domain transfer performance of supervised neural text segmentation in the educational domain.
no code implementations • 23 Apr 2024 • Kevin Stowe, Benny Longwill, Alyssa Francis, Tatsuya Aoyama, Debanjan Ghosh, Swapna Somasundaran
Natural language generation tools are powerful and effective for generating content.
no code implementations • 28 Oct 2022 • Sophia Chan, Swapna Somasundaran, Debanjan Ghosh, Mengxuan Zhao
We describe the AGReE system, which takes user-submitted passages as input and automatically generates grammar practice exercises that can be completed while reading.
no code implementations • WS 2020 • Swapna Somasundaran, Xianyang Chen, Michael Flor
This paper studies emotion arcs in student narratives.
1 code implementation • 3 Jan 2020 • Goran Glavaš, Swapna Somasundaran
Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval.
no code implementations • WS 2019 • Michael Flor, Swapna Somasundaran
This study explores the relation between lexical concreteness and narrative text quality.
no code implementations • TACL 2018 • Swapna Somasundaran, Michael Flor, Martin Chodorow, Hillary Molloy, Binod Gyawali, Laura McCulla
This work lays the foundation for automated assessments of narrative quality in student writing.
no code implementations • WS 2017 • Michael Flor, Swapna Somasundaran
Our lexical cohesion system achieves accuracy comparable to previously published baseline results.
no code implementations • COLING 2016 • Swapna Somasundaran, Brian Riordan, Binod Gyawali, Su-Youn Yoon
This work investigates whether the development of ideas in writing can be captured by graph properties derived from the text.