Search Results for author: Hinrich Schuetze

Found 13 papers, 3 papers with code

Language Models with Rationality

no code implementations23 May 2023 Nora Kassner, Oyvind Tafjord, Ashish Sabharwal, Kyle Richardson, Hinrich Schuetze, Peter Clark

To address this, our goals are to make model beliefs and their inferential relationships explicit, and to resolve inconsistencies that may exist, so that answers are supported by interpretable chains of reasoning drawn from a consistent network of beliefs.

Question Answering

Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments

1 code implementation Findings (ACL) 2022 Antonis Maronikolakis, Axel Wisiorek, Leah Nann, Haris Jabbar, Sahana Udupa, Hinrich Schuetze

Building on current work on multilingual hate speech (e. g., Ousidhoum et al. (2019)) and hate speech reduction (e. g., Sap et al. (2020)), we present XTREMESPEECH, a new hate speech dataset containing 20, 297 social media passages from Brazil, Germany, India and Kenya.

Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data

no code implementations EACL (AdaptNLP) 2021 Sanjeev Kumar Karn, Francine Chen, Yan-Ying Chen, Ulli Waltinger, Hinrich Schuetze

Interleaved texts, where posts belonging to different threads occur in a sequence, commonly occur in online chat posts, so that it can be time-consuming to quickly obtain an overview of the discussions.

Disentanglement Few-Shot Learning +1

Nonsymbolic Text Representation

no code implementations3 Oct 2016 Hinrich Schuetze, Heike Adel, Ehsaneddin Asgari

We introduce the first generic text representation model that is completely nonsymbolic, i. e., it does not require the availability of a segmentation or tokenization method that attempts to identify words or other symbolic units in text.

Denoising

Two SVDs produce more focal deep learning representations

no code implementations16 Jan 2013 Hinrich Schuetze, Christian Scheible

A key characteristic of work on deep learning and neural networks in general is that it relies on representations of the input that support generalization, robust inference, domain adaptation and other desirable functionalities.

Domain Adaptation Vocal Bursts Valence Prediction

Cutting Recursive Autoencoder Trees

no code implementations13 Jan 2013 Christian Scheible, Hinrich Schuetze

This makes the analysis of learned structures particularly difficult.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.