Multitask Learning for Darpa Lorelei's Situation Frame Extraction Task

Karan Singla, Shrikanth NarayananICASSP 2020 · OpenReview

Abstract

This paper describes a novel approach of multitask learning for an end-to-end optimization technique for document classification. The application motivation comes from the need to extract "Situation Frames (SF)" from a document within the context of DARPA’s LORELEI program targeting humanitarian assistance and disaster relief. We show the benefit of our approach for extracting SF: which includes extracting document types and then linking them to entities. We jointly train a hierarchical document classifier and an auto-encoder using a shared word-level bottleneck layers. Our architecture can exploit additional monolingual corpora in addition to labelled data for classification, thus helping it to generalize over a bigger vocabulary. We evaluate these approaches over standard datasets for this task. Our methods show improvements for both document type prediction and entity linking.
BibTeX
@inproceedings{singla2020multitask,
  author = {Karan Singla and Shrikanth Narayanan},
  title = {{Multitask Learning for Darpa Lorelei's Situation Frame Extraction Task}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2020},
  url = {https://openreview.net/forum?id=au3ivx1lRJ2},
}

Loading related content...

Figure