TY - JOUR
AU - 
AB - A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories 1 2 3 4 Nasrin Mostafazadeh , Nathanael Chambers , Xiaodong He , Devi Parikh , 4 3 3 1,5 Dhruv Batra , Lucy Vanderwende , Pushmeet Kohli , James Allen 1 University of Rochester, 2 United States Naval Academy, 3 Microsoft Research, 4 Virginia Tech, 5 The Institute for Human & Machine Cognition {nasrinm,james}@cs.rochester.edu, nchamber@usna.edu, {parikh,dbatra}@vt.edu, {xiaohe,lucyv,pkohli}@microsoft.com Abstract Recently, there has been a renewed interest in story and narrative understanding based on progress made Representation and learning of commonsense in core NLP tasks. This ranges from generic story knowledge is one of the foundational prob- telling models to building systems which can com- lems in the quest to enable deep language un- pose meaningful stories in collaboration with hu- derstanding. This issue is particularly chal- mans (Swanson and Gordon, 2008). Perhaps the lenging for understanding casual and corre- biggest challenge of story understanding (and story lational relationships between events. While generation) is having commonsense knowledge for this topic has received a lot of interest in the NLP community, research has been hindered the interpretation of narrative events. The question by the lack of a proper evaluation framework. 
TI - A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
JF - Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
DO - 10.18653/v1/n16-1098
DA - 2016-01-01
UR - https://www.deepdyve.com/lp/unpaywall/a-corpus-and-cloze-evaluation-for-deeper-understanding-of-commonsense-QDYE3n9krm
DP - DeepDyve
ER -