Year: 2019
Type: conference-paper
Abstract: Recognizing the internal structure of events is a challenging language processing task of great importance for text understanding.We present a supervised model for automatically identifying when one event is a subevent of another.Building on prior work, we introduce several novel features, in particular discourse and narrative features, that significantly improve upon prior state-of-the-art performance.Error analysis further demonstrates the utility of these features.We evaluate our model on the only two annotated corpora with event hierarchies: HiEve and the Intelligence Community corpus.No prior system has been evaluated on both corpora.Our model outperforms previous systems on both corpora, achieving 0.74 BLANC F 1 on the Intelligence Community corpus and 0.70 F 1 on the HiEve corpus, respectively a 15 and 5 percentage point improvement over previous models.
DOI: 10.18653/v1/p19-1471
Authors: Mohammed Aldawsari, Mark Finlayson
Institution: Florida International University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2952361887