Search Results for author:
Found 18 papers, 1 papers with code
Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets
Filtering and annotating textual data are routine tasks in many areas, like social media or news analytics.
POV Learning: Individual Alignment of Multimodal Models using Human Perception
Our findings suggest that exploiting individual perception signals for the machine learning of subjective human assessments provides a valuable cue for individual alignment.
Heterogeneous Graph-based Trajectory Prediction using Local Map Context and Social Interactions
Precisely predicting the future trajectories of surrounding traffic participants is a crucial but challenging problem in autonomous driving, due to complex interactions between traffic agents, map context and traffic rules.
Context-driven Visual Object Recognition based on Knowledge Graphs
The experimental results provide evidence that the contextual views influence the image representations in the DNN differently and therefore lead to different predictions for the same images.
Signing the Supermask: Keep, Hide, Invert
Through this extension and adaptations of initialization methods, we achieve a pruning rate of up to 99%, while still matching or exceeding the performance of various baseline and previous models.
A Survey on Visual Transfer Learning using Knowledge Graphs
KGs can represent auxiliary knowledge either in an underlying graph-structured schema or in a vector-based knowledge graph embedding.
InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline
Digital Humanities and Computational Literary Studies apply text mining methods to investigate literature.
Learning Visual Models using a Knowledge Graph as a Trainer
However, due to the sole dependence on the image data distribution of the training domain, these models tend to fail when applied to a target domain that differs from their source domain.
Towards Learning Cross-Modal Perception-Trace Models
In this paper we empirically investigate the difference between human perception and context heuristics of basic embedding models.
Which Knowledge Graph Is Best for Me?
Furthermore, we proposed a framework for finding the most suitable knowledge graph for a given setting.
Linking Tweets with Monolingual and Cross-Lingual News using Transformed Word Embeddings
But the gap in word usage between informal social media content such as tweets and diligently written content (e. g. news articles) make such assembling difficult.
Describing Natural Images Containing Novel Objects with Knowledge Guided Assitance
Images in the wild encapsulate rich knowledge about varied abstract concepts and cannot be sufficiently described with models built only using image-caption pairs containing selected objects.
Knowledge Fusion via Embeddings from Text, Knowledge Graphs, and Images
We present a baseline approach for cross-modal knowledge fusion.
xLiD-Lexica: Cross-lingual Linked Data Lexica
In this paper, we introduce our cross-lingual linked data lexica, called xLiD-Lexica, which are constructed by exploiting the multilingual Wikipedia and linked data resources from Linked Open Data (LOD).
RECSA: Resource for Evaluating Cross-lingual Semantic Annotation
To support this line of research we developed what we believe could serve as a gold standard Resource for Evaluating Cross-lingual Semantic Annotation (RECSA).
