Extracting Fine-Grained Economic Events from Business News

Our presentation for FNP-FNS at COLING 2020 (1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation).
Abstract: Based on a recently developed fine-grained event extraction dataset for the economic domain,we present in a pilot study for supervised economic event extraction. We investigate how a state-of-the-art model for event extraction performs on the trigger and argument identification and classification. While F1-scores of above 50% are obtained on the task of trigger identification, we observe a large gap in performance compared to results on the benchmark ACE05 dataset. We show that single-token triggers do not provide sufficient discriminative information for a fine-grained event detection setup in a closed domain such as economics, since many classes have a large degree of lexico-semantic and contextual overlap.
📝 Paper full-text: TBA
📽️ Slides: TBA
💾 Replication data and source code: osf.io/j63h9
🌐 Link to my personal site: jacobsgill.es
💹 More info on the SENTiVENT project: www.lt3.ugent.be/projects/eve...