LSDSem 2017: Exploring Data Generation Methods for the Story Cloze Test

Michael Bugert, Yevgeniy Puzikov, Andreas Rücklé, Judith Eckle-Kohler, Teresa Martin, Eugenio Martínez-Cámara, Daniil Sorokin, Maxime Peyrard, Iryna Gurevych


Abstract
The Story Cloze test is a recent effort in providing a common test scenario for text understanding systems. As part of the LSDSem 2017 shared task, we present a system based on a deep learning architecture combined with a rich set of manually-crafted linguistic features. The system outperforms all known baselines for the task, suggesting that the chosen approach is promising. We additionally present two methods for generating further training data based on stories from the ROCStories corpus.
Anthology ID:
W17-0908
Volume:
Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics
Month:
April
Year:
2017
Address:
Valencia, Spain
Venue:
LSDSem
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
56–61
Language:
URL:
https://aclanthology.org/W17-0908
DOI:
10.18653/v1/W17-0908
Bibkey:
Cite (ACL):
Michael Bugert, Yevgeniy Puzikov, Andreas Rücklé, Judith Eckle-Kohler, Teresa Martin, Eugenio Martínez-Cámara, Daniil Sorokin, Maxime Peyrard, and Iryna Gurevych. 2017. LSDSem 2017: Exploring Data Generation Methods for the Story Cloze Test. In Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, pages 56–61, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
LSDSem 2017: Exploring Data Generation Methods for the Story Cloze Test (Bugert et al., LSDSem 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/W17-0908.pdf
Code
 UKPLab/lsdsem2017-story-cloze
Data
ROCStories