Incorporation of company-related factual knowledge into pre-trained language models for stock-related spam tweet filtering
Natural language processing for finance has gained significant attention from both
academia and the industry as the continuously increasing amount of financial texts has …
academia and the industry as the continuously increasing amount of financial texts has …
Combining deep neural reranking and unsupervised extraction for multi-query focused summarization
P Seeberger, K Riedhammer - arXiv preprint arXiv:2302.01148, 2023 - arxiv.org
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 disaster …
domain of event tracking; participants' systems extract important facts from several disaster …
Multi-Query Focused Disaster Summarization via Instruction-Based Prompting
P Seeberger, K Riedhammer - arXiv preprint arXiv:2402.09008, 2024 - arxiv.org
Automatic summarization of mass-emergency events plays a critical role in disaster
management. The second edition of CrisisFACTS aims to advance disaster summarization …
management. The second edition of CrisisFACTS aims to advance disaster summarization …
A dataset of Open Source Intelligence (OSINT) Tweets about the Russo-Ukrainian war
J Niu, M Stillman, P Seeberger, A Kruspe - arXiv preprint arXiv …, 2024 - arxiv.org
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 or …
data. It has become a frequent topic of conversation on social media, where private users or …
Information Type Classification with Contrastive Task-Specialized Sentence Encoders
User-generated information content has become an important information source in crisis
situations. However, classification models suffer from noise and event-related biases which …
situations. However, classification models suffer from noise and event-related biases which …
Classification de tweets en situation d'urgence pour la gestion de crises
R Meunier, L Moudjari, F Benamara… - 18e Conférence en …, 2023 - hal.science
Le traitement de données provenant de réseaux sociaux en temps réel est devenu une outil
attractifdans les situations d'urgence, mais la surcharge d'informations reste un défi à …
attractifdans les situations d'urgence, mais la surcharge d'informations reste un défi à …
Crisis2Sum: An Exploratory Study on Disaster Summarization from Multiple Streams
P Seeberger, K Riedhammer - ISCRAM Proceedings, 2024 - ojs.iscram.org
Automatic summarization of natural and human-made disaster events is an important area to
increase situational awareness for human response organizations and disaster …
increase situational awareness for human response organizations and disaster …