no code implementations • EMNLP (CMCL) 2020 • Michaela Regneri, Diane King, Fahreen Walji, Olympia Palikara
Different aspects of language processing have been shown to be sensitive to priming but the findings of studies examining priming effects in adolescents with Autism Spectrum Disorder (ASD) and Developmental Language Disorder (DLD) have been inconclusive.
no code implementations • 24 Apr 2024 • Michaela Regneri, Alhassan Abdelhalim, Sören Laue
We present a novel approach to detecting noun abstraction within a large language model (LLM).
no code implementations • 29 Jul 2019 • Michaela Regneri, Julia S. Georgi, Jurij Kost, Niklas Pietsch, Sabine Stamm
We present an approach to compute the monetary value of individual data points, in context of an automated decision system.
no code implementations • 17 Jul 2018 • Michaela Regneri, Malte Hoffmann, Jurij Kost, Niklas Pietsch, Timo Schulz, Sabine Stamm
Predictive geometric models deliver excellent results for many Machine Learning use cases.
no code implementations • ACL 2016 • Seid Muhie Yimam, Heiner Ulrich, von L, Tatiana esberger, Marcel Rosenbach, Michaela Regneri, Alex Panchenko, er, Franziska Lehmann, Uli Fahrer, Chris Biemann, Kathrin Ballweg
no code implementations • 23 Feb 2015 • Marcus Rohrbach, Anna Rohrbach, Michaela Regneri, Sikandar Amin, Mykhaylo Andriluka, Manfred Pinkal, Bernt Schiele
To attack the second challenge, recognizing composite activities, we leverage the fact that these activities are compositional and that the essential components of the activities can be obtained from textual descriptions or scripts.
no code implementations • LREC 2014 • Michaela Regneri, Rui Wang, Manfred Pinkal
Paraphrases and paraphrasing algorithms have been found of great importance in various natural language processing tasks.
no code implementations • TACL 2013 • Michaela Regneri, Marcus Rohrbach, Dominikus Wetzel, Stefan Thater, Bernt Schiele, Manfred Pinkal
Recent work has shown that the integration of visual information into text-based models can substantially improve model predictions, but so far only visual information extracted from static images has been used.