no code implementations • SemEval (NAACL) 2022 • Jan Pfister, Sebastian Wankerl, Andreas Hotho
Structured Sentiment Analysis is the task of extracting sentiment tuples in a graph structure commonly from review texts.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)
no code implementations • SemEval (NAACL) 2022 • Dirk Wangsadirdja, Felix Heinickel, Simon Trapp, Albin Zehe, Konstantin Kobs, Andreas Hotho
We present a system that creates pair-wise cosine and arccosine sentence similarity matrices using multilingual sentence embeddings obtained from pre-trained SBERT and Universal Sentence Encoder (USE) models respectively.
no code implementations • SemEval (NAACL) 2022 • Stefan Heil, Karina Kopp, Albin Zehe, Konstantin Kobs, Andreas Hotho
This paper introduces our submission for the SemEval 2022 Task 8: Multilingual News Article Similarity.
no code implementations • 28 Mar 2024 • Andrzej Dulny, Paul Heinisch, Andreas Hotho, Anna Krause
GrINd offers a promising approach for forecasting physical systems from sparse, scattered observational data, extending the applicability of deep learning methods to real-world scenarios with limited data availability.
no code implementations • 27 Mar 2024 • Pascal Janetzky, Florian Gallusser, Simon Hentschel, Andreas Hotho, Anna Krause
We demonstrate that leveraging pre-trained weather models improves the NDVI estimates compared to learning an NDVI model from scratch.
no code implementations • 17 Jan 2024 • Tom Völker, Jan Pfister, Tobias Koopmann, Andreas Hotho
The ever-growing corpus of scientific literature presents significant challenges for researchers with respect to discovery, management, and annotation of relevant publications.
1 code implementation • 6 Oct 2023 • Tobias Koopmann, Jan Pfister, André Markus, Astrid Carolus, Carolin Wienrich, Andreas Hotho
Analyzing, understanding, and describing human behavior is advantageous in different settings, such as web browsing or traffic navigation.
no code implementations • 26 Jun 2023 • Paul Heinisch, Andrzej Dulny, Anna Krause, Andreas Hotho
Modeling data obtained from dynamical systems has gained attention in recent years as a challenging task for machine learning models.
1 code implementation • 9 Jun 2023 • Andrzej Dulny, Andreas Hotho, Anna Krause
The dataset focuses on predicting the evolution of a dynamical system from low-resolution, unstructured measurements.
no code implementations • 11 May 2023 • Albin Zehe, Julian Schröter, Andreas Hotho
Suspense is an important tool in storytelling to keep readers engaged and wanting to read more.
1 code implementation • 15 Feb 2023 • Christian Rack, Konstantin Kobs, Tamara Fernando, Andreas Hotho, Marc Erich Latoschik
Furthermore, we extended this evaluation using an independent dataset that features completely different users, tasks, and three different XR devices.
1 code implementation • 23 Nov 2022 • Konstantin Kobs, Michael Steininger, Andreas Hotho
Therefore, we present Language-Guided Zero-Shot Deep Metric Learning (LanZ-DML) as a new DML setting in which users control the properties that should be important for image representations without training data by only using natural language.
no code implementations • 14 Oct 2022 • Vincenzo Perri, Lisi Qarkaxhija, Albin Zehe, Andreas Hotho, Ingo Scholtes
Natural Language Processing and Machine Learning have considerably advanced Computational Literary Studies.
1 code implementation • 4 Oct 2022 • Konstantin Kobs, Andreas Hotho
Deep Metric Learning trains a neural network to map input images to a lower-dimensional embedding space such that similar images are closer together than dissimilar images.
no code implementations • 2 Oct 2022 • Christian Schell, Andreas Hotho, Marc Erich Latoschik
Reliable and robust user identification and authentication are important and often necessary requirements for many digital services.
no code implementations • 7 Jul 2022 • Padraig Davidson, Michael Steininger, André Huhn, Anna Krause, Andreas Hotho
Due to its chaotic nature and massive amounts of datapoints, timeseries are hard to label manually.
no code implementations • 9 Jun 2022 • Julian Tritscher, Fabian Gwinner, Daniel Schlör, Anna Krause, Andreas Hotho
Recent estimates report that companies lose 5% of their revenue to occupational fraud.
1 code implementation • ICCV 2021 • Konstantin Kobs, Michael Steininger, Andrzej Dulny, Andreas Hotho
In this paper, we investigate this by conducting a two-step analysis to extract and compare the learned visual features of the same model architecture trained with different loss functions: First, we compare the learned features on the pixel level by correlating saliency maps of the same input images.
no code implementations • 17 Jan 2022 • Alexander Dallmann, Johannes Kohlmann, Daniel Zoller, Andreas Hotho
We find that SIR models can be employed effectively for item recommendation in Dota 2.
no code implementations • 15 Nov 2021 • Andrzej Dulny, Andreas Hotho, Anna Krause
Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs).
no code implementations • 8 Oct 2021 • Padraig Davidson, Michael Steininger, Florian Lautenschlager, Anna Krause, Andreas Hotho
Sensor-equipped beehives allow monitoring the living conditions of bees.
no code implementations • 27 Jul 2021 • Alexander Dallmann, Daniel Zoller, Andreas Hotho
Then we evaluate all models on a target set sampled by the two different sampling strategies, uniform random sampling and sampling by popularity with the commonly used target set size of 100, compute the model ranking for each strategy and compare them with each other.
no code implementations • EACL 2021 • Albin Zehe, Leonard Konle, Lea Katharina D{\"u}mpelmann, Evelyn Gius, Andreas Hotho, Fotis Jannidis, Lucas Kaufmann, Markus Krug, Frank Puppe, Nils Reiter, Annekea Schreiber, Nathalie Wiedmer
This paper introduces the novel task of scene segmentation on narrative texts and provides an annotated corpus, a discussion of the linguistic and narrative properties of the task and baseline experiments towards automatic solutions.
no code implementations • 9 Dec 2020 • Michael Steininger, Daniel Abel, Katrin Ziegler, Anna Krause, Heiko Paeth, Andreas Hotho
Climate models are an important tool for the assessment of prospective climate change effects but they suffer from systematic and representation errors, especially for precipitation.
1 code implementation • 3 Dec 2020 • Michael Fischer, Konstantin Kobs, Andreas Hotho
However, fully-automatic approaches usually enhance the image in a black-box manner that does not give the user any control over the optimization process, possibly leading to edited images that do not subjectively appeal to the user.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Konstantin Kobs, Tobias Koopmann, Albin Zehe, David Fernes, Philipp Krop, Andreas Hotho
Whenever researchers write a paper, the same question occurs: {``}Where to submit?
no code implementations • LREC 2020 • Daniel Schl{\"o}r, Albin Zehe, Konstantin Kobs, Blerta Veseli, Franziska Westermeier, Larissa Br{\"u}bach, Daniel Roth, Marc Erich Latoschik, Andreas Hotho
Humans frequently are able to read and interpret emotions of others by directly taking verbal and non-verbal signals in human-to-human communication into account or to infer or even experience emotions from mediated stories.
2 code implementations • 17 Mar 2020 • Daniel Schlör, Markus Ring, Andreas Hotho
Our experiments indicate that our model solves stability issues and outperforms the original NALU model in means of arithmetic precision and convergence.
no code implementations • 10 Mar 2020 • Padraig Davidson, Michael Steininger, Florian Lautenschlager, Konstantin Kobs, Anna Krause, Andreas Hotho
Precision beekeeping allows to monitor bees' living conditions by equipping beehives with sensors.
1 code implementation • 6 Mar 2020 • Konstantin Kobs, Michael Steininger, Albin Zehe, Florian Lautenschlager, Andreas Hotho
One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally.
no code implementations • 18 Feb 2020 • Michael Steininger, Konstantin Kobs, Albin Zehe, Florian Lautenschlager, Martin Becker, Andreas Hotho
In this paper, we advocate a paradigm shift for LUR models: We propose the Data-driven, Open, Global (DOG) paradigm that entails models based on purely data-driven approaches using only openly and globally available data.
no code implementations • SEMEVAL 2019 • Albin Zehe, Lena Hettinger, Stefan Ernst, Christian Hauptmann, Andreas Hotho
This paper describes our system for the SemEval 2019 Task 4 on hyperpartisan news detection.
no code implementations • 27 Sep 2018 • Markus Ring, Daniel Schlör, Dieter Landes, Andreas Hotho
We use the three approaches for generating flow-based network traffic based on the CIDDS-001 data set.
no code implementations • SEMEVAL 2018 • Lena Hettinger, Alex Dallmann, er, Albin Zehe, Thomas Niebler, Andreas Hotho
In this paper we describe our system for SemEval-2018 Task 7 on classification of semantic relations in scientific literature for clean (subtask 1. 1) and noisy data (subtask 1. 2).
no code implementations • 16 Apr 2018 • Lena Hettinger, Alexander Dallmann, Albin Zehe, Thomas Niebler, Andreas Hotho
Due to these changes Classification of Relations using Embeddings (ClaiRE) achieved an improved F1 score of 75. 11% for the first subtask and 81. 44% for the second.
no code implementations • 14 Dec 2017 • Mark Kibanov, Martin Becker, Juergen Mueller, Martin Atzmueller, Andreas Hotho, Gerd Stumme
This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized.
1 code implementation • 30 Jun 2017 • Alexander Dallmann, Alexander Grimm, Christian Pölitz, Daniel Zoller, Andreas Hotho
Recently, Recurrent Neural Networks (RNNs) have been applied to the task of session-based recommendation.
no code implementations • 21 May 2017 • Thomas Niebler, Martin Becker, Christian Pölitz, Andreas Hotho
To solve this, we propose to utilize a metric learning approach to improve existing semantic relatedness measures by learning from additional information, such as explicit human feedback.
no code implementations • 28 Nov 2016 • Fotis Jannidis, Isabella Reger, Albin Zehe, Martin Becker, Lena Hettinger, Andreas Hotho
With regard to a computational representation of literary plot, this paper looks at the use of sentiment analysis for happy ending detection in German novels.