Der Login über E-Mail und Passwort wird in Kürze abgeschaltet. Für Externe steht ab sofort der Login über ORCID zur Verfügung.
The login via e-mail and password will be retired in the near future. External uses can login via ORCID from now on.
 
File access restricted

Fine-tuned model weights for Stance Detection Benchmark System

Thumbnail Image

Files

fine_tuned_models.zip (Fine-tuned model weights) (2.32 GB)

Date

2021-07-03

Type

Model

Authors

Schiller, Benjamin
Daxenberger, JohannesORCID 0000-0002-7385-5654
Gurevych, IrynaORCID 0000-0003-2187-7621

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

This collection includes model weights (BERT-based), fine-tuned in a multi-task setting on 10 heterogeneous stance detection datasets. For more information, please refer to the paper and the GitHub repository linked in the paper. DISCLAIMER: The user acknowledges and agrees that the data is provided on an “as­-is” basis and that the licensor makes no representations or warranties of any kind.

Keywords

Stance Detection, Benchmark, Model weights

Citation

Identifier

https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/2848

Endorsement

Related Resources

Is Cited By
https://arxiv.org/abs/2001.01565
https://doi.org/10.1007/s13218-021-00714-w

DFG Classification

4.43-04 Künstliche Intelligenz und Maschinelle Lernverfahren
4.43-05 Bild- und Sprachverarbeitung, Computergraphik und Visualisierung, Human Computer Interaction, Ubiquitous und Wearable Computing

Project(s)

PTJ | 03VP02540 | ArgumenText

Faculty

Collections

Argument Mining

License

In Copyright
Except where otherwise noted, this license is described as In Copyright