Papers by Frank Puppe

2 papers
Detecting Scenes in Fiction: A new Segmentation Task (2021.eacl-main)

Copied to clipboard

Challenge: Text segmentation is a long standing issue in the area of natural language processing . even modern methods struggle with processing text longer than a couple of sentences or paragraphs .
Approach: They introduce the task of scene segmentation on narrative texts and provide an annotated corpus . they discuss linguistic and narrative properties of the task and provide baseline experiments .
Outcome: The proposed task is very challenging and the results are impressive.
ADEA: An Argumentative Dialogue Dataset on Ethical Issues Concerning Future A.I. Applications (2024.lrec-main)

Copied to clipboard

Challenge: Introducing ADEA: a dataset that captures online dialogues and focuses on ethical issues related to future AI applications.
Approach: They propose a German dataset that captures online dialogues on ethical issues . the dataset includes over 2800 labeled user utterances on four different topics . they use an argument graph as the system's knowledge base and an annotation scheme .
Outcome: The proposed dataset includes over 2800 user utterances on four ethical topics . the aim is to improve knowledge about AI ethics topics through argumentative dialogues .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations