2 citations · 5 across the 12 of their papers we have counts for
12 papers
Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts
Steffen Freisinger, Philipp Seeberger, Thomas Ranzenberger +2
Long transcripts are costly inputs for downstream NLP systems and often contain irrelevant context. We study query-conditioned topic localization: predicting the sentence span in a…
Evaluation Pitfalls and Challenges in Multimedia Event Extraction
Philipp Seeberger, Steffen Freisinger, Tobias Bocklet +1
Multimedia event extraction aims to jointly identify events and their arguments across multiple modalities, such as text and images, to support more comprehensive event understandi…
Reading Between the Waves: Robust Topic Segmentation Using Inter-Sentence Audio Features
Steffen Freisinger, Philipp Seeberger, Tobias Bocklet +1
Spoken content, such as online videos and podcasts, often spans multiple topics, which makes automatic topic segmentation essential for user navigation and downstream applications.…
Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation
Steffen Freisinger, Philipp Seeberger, Thomas Ranzenberger +2
Segmenting speech transcripts into thematic sections benefits both downstream processing and users who depend on written text for accessibility. We introduce a novel approach to hi…
Generalizing to Unseen Disaster Events: A Causal View
Philipp Seeberger, Steffen Freisinger, Tobias Bocklet +1
Due to the rapid growth of social media platforms, these tools have become essential for monitoring information during ongoing disaster events. However, extracting valuable insight…
A dataset of Open Source Intelligence (OSINT) Tweets about the Russo-Ukrainian war
Johannes Niu, Mila Stillman, Philipp Seeberger +1
Open Source Intelligence (OSINT) refers to intelligence efforts based on freely available data. It has become a frequent topic of conversation on social media, where private users…
MMUTF: Multimodal Multimedia Event Argument Extraction with Unified Template Filling
Philipp Seeberger, Dominik Wagner, Korbinian Riedhammer
With the advancement of multimedia technologies, news documents and user-generated content are often represented as multiple modalities, making Multimedia Event Extraction (MEE) an…
Optimized Speculative Sampling for GPU Hardware Accelerators
Dominik Wagner, Seanie Lee, Ilja Baumann +3
In this work, we optimize speculative sampling for parallel hardware accelerators to improve sampling speed. We notice that substantial portions of the intermediate matrices necess…
Multi-Query Focused Disaster Summarization via Instruction-Based Prompting
Philipp Seeberger, Korbinian Riedhammer
Automatic summarization of mass-emergency events plays a critical role in disaster management. The second edition of CrisisFACTS aims to advance disaster summarization based on mul…
Information Type Classification with Contrastive Task-Specialized Sentence Encoders
Philipp Seeberger, Tobias Bocklet, Korbinian Riedhammer
User-generated information content has become an important information source in crisis situations. However, classification models suffer from noise and event-related biases which…
Combining Deep Neural Reranking and Unsupervised Extraction for Multi-Query Focused Summarization
Philipp Seeberger, Korbinian Riedhammer
The CrisisFACTS Track aims to tackle challenges such as multi-stream fact-finding in the domain of event tracking; participants' systems extract important facts from several disast…
Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning
Philipp Seeberger, Korbinian Riedhammer
Social media has become an important information source for crisis management and provides quick access to ongoing developments and critical information. However, classification mo…