Story Cloze Ending Selection Baselines and Data Examination

Todor Mihaylov, Anette Frank


Abstract
This paper describes two supervised baseline systems for the Story Cloze Test Shared Task (Mostafazadeh et al., 2016a). We first build a classifier using features based on word embeddings and semantic similarity computation. We further implement a neural LSTM system with different encoding strategies that try to model the relation between the story and the provided endings. Our experiments show that a model using representation features based on average word embedding vectors over the given story words and the candidate ending sentences words, joint with similarity features between the story and candidate ending representations performed better than the neural models. Our best model based on achieves an accuracy of 72.42, ranking 3rd in the official evaluation.
Anthology ID:
W17-0913
Volume:
Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Michael Roth, Nasrin Mostafazadeh, Nathanael Chambers, Annie Louis
Venue:
LSDSem
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
87–92
Language:
URL:
https://aclanthology.org/W17-0913
DOI:
10.18653/v1/W17-0913
Bibkey:
Cite (ACL):
Todor Mihaylov and Anette Frank. 2017. Story Cloze Ending Selection Baselines and Data Examination. In Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, pages 87–92, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Story Cloze Ending Selection Baselines and Data Examination (Mihaylov & Frank, LSDSem 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/W17-0913.pdf
Data
StoryCloze