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 F1 on the Intelligence Community corpus and 0.70 F1 on the HiEve corpus, respectively a 15 and 5 percentage point improvement over previous models.

Highlights

  • An event is something that occurs in a certain place at a certain time (Pustejovsky et al, 2003)

  • The results of the performance averaged across all five folds on the three classes (PC, child relationship (CP) and no relation (NoRel)) are shown in Table 4 using both evaluation metrics on both corpora

  • It is not clear to us how Araki et al handled the direction of the subevent relation, we take the average of our model classes (PC and CP) and compare it with the subevent class in Araki et al.’s work

Read more

Summary

Introduction

An event is something that occurs in a certain place at a certain time (Pustejovsky et al, 2003). We say that an event e1 is a parent event of event e2, and e2 is a child event of e1 if (1) e1 is collector event that contains a complex sequence of activities; (2) e2 is one of these activities; and (3) e2 is spatially and temporally contained within e1 (i.e., e2 occur at the same time and same place as e1) (Hovy et al, 2013; Glavasand Snajder, 2014b) This subevent relationship is independent of other types of relationships, e.g., causal relationship between the events.

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.