Mustafa Ocal

School of Computing and Information Sciences

Lecture Information:
  • October 28, 2020
  • 9:30 AM
  • Zoom: https://fiu.zoom.us/j/7963519961

Speaker Bio

Mustafa Ocal is a Ph.D. candidate at the School of Computing and Information Sciences, Florida International University, under the supervision of Professor Mark A. Finlayson. He conducts research at Cognition, Narrative, and Culture Laboratory (Cognac Lab). His research interest lies in Natural Language Processing, with a focus on Temporal Information Extraction. He holds a B.Sc. degree in Computer Engineering from Gazi University, Turkey in 2017.

Description

Extracting temporal analysis of narratives is useful for many Natural Language Processing (NLP) applications such as question answering, summarization, information extraction, and other applications. There are various tasks of extracting temporal analysis: Automatic TimeML annotation, extracting timelines, or duration extraction. There have been several attempts to extract temporal analysis, however, they suffer from many problems. Firstly, they do not provide automatic annotation methods for TimeML link types such as subordination links and aspectual links. Secondly, for timeline extraction, they only deal with a small subset of temporal relations and exclude a large portion of temporal relations. Thirdly, instead of predicting approximate duration for events, they provide binary classification. The proposed approach is implementing a system that addresses these issues and provides complete automatic TimeML annotations, extracts the exact timeline, and predicts approximate durations of events.