Inflation Narratives from a Machine Learning Perspective
Research output: Contributions to collected editions/works › Published abstract in conference proceedings › Research › peer-review
Standard
Digital Total - Computing & Data Science an der Universität Hamburg und in der Wissenschaftsmetropole Hamburg: Book of Abstracts. ed. / Martin Semmann; Seid Muhie Yimam; Katrin Schöning-Stierand; Chris Biemann. Hamburg: Universitat Hamburg, 2023. p. 143.
Research output: Contributions to collected editions/works › Published abstract in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Inflation Narratives from a Machine Learning Perspective
AU - Möller, Cedric
AU - Huang, Junbo
AU - Weinig, Max Valentin
AU - Usbeck, Ricardo
AU - Fritsche, Ulrich
PY - 2023/10/1
Y1 - 2023/10/1
N2 - Inflation narratives explain inflation changes and affect expectations. Manu- ally identifying them is cumbersome, prompting the need for scalable algo- rithms. Narratives comprise events, causal relations, and arguments, repre- sented as graphs with event and argument nodes. Causal relations indicate cause-and-effect relationships between events using directed edges. Our main objective is to extract narratives from text to enhance a knowledge graph for analysis like social network analysis or edge prediction. We address two sub- problems: event extraction, involving event type and argument identification, and event deduplication. Second, we extract causal relations as expressed by authors, not necessarily true causal links between events in the text.
AB - Inflation narratives explain inflation changes and affect expectations. Manu- ally identifying them is cumbersome, prompting the need for scalable algo- rithms. Narratives comprise events, causal relations, and arguments, repre- sented as graphs with event and argument nodes. Causal relations indicate cause-and-effect relationships between events using directed edges. Our main objective is to extract narratives from text to enhance a knowledge graph for analysis like social network analysis or edge prediction. We address two sub- problems: event extraction, involving event type and argument identification, and event deduplication. Second, we extract causal relations as expressed by authors, not necessarily true causal links between events in the text.
KW - Informatics
UR - https://www.hcds.uni-hamburg.de/en/current/all-events/digital-total/digital-total-boa.pdf
M3 - Published abstract in conference proceedings
SP - 143
BT - Digital Total - Computing & Data Science an der Universität Hamburg und in der Wissenschaftsmetropole Hamburg
A2 - Semmann, Martin
A2 - Yimam, Seid Muhie
A2 - Schöning-Stierand, Katrin
A2 - Biemann, Chris
PB - Universitat Hamburg
CY - Hamburg
T2 - Digital Total - Computing & Data Science an der Universität Hamburg und in der Wissenschaftsmetropole Hamburg
Y2 - 9 October 2023 through 10 October 2023
ER -