no code implementations • ACL 2020 • Khalid Al Khatib, Michael V{\"o}lske, Shahbaz Syed, Nikolay Kolyada, Benno Stein
Predicting the persuasiveness of arguments has applications as diverse as writing assistance, essay scoring, and advertising.
no code implementations • WS 2019 • Shahbaz Syed, Michael V{\"o}lske, Nedim Lipka, Benno Stein, Hinrich Sch{\"u}tze, Martin Potthast
In this paper, we report on the results of the TL;DR challenge, discussing an extensive manual evaluation of the expected properties of a good summary based on analyzing the comments provided by human annotators.
no code implementations • WS 2018 • Shahbaz Syed, Michael V{\"o}lske, Martin Potthast, Nedim Lipka, Benno Stein, Hinrich Sch{\"u}tze
The TL;DR challenge fosters research in abstractive summarization of informal text, the largest and fastest-growing source of textual data on the web, which has been overlooked by summarization research so far.
no code implementations • WS 2017 • Michael V{\"o}lske, Martin Potthast, Shahbaz Syed, Benno Stein
Recent advances in automatic text summarization have used deep neural networks to generate high-quality abstractive summaries, but the performance of these models strongly depends on large amounts of suitable training data.