5 Hits in 1.5 sec

MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants

Simon Ostermann, Michael Roth, Manfred Pinkal
2019 Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)  
We introduce MCScript2.0, a machine comprehension corpus for the end-to-end evaluation of script knowledge.  ...  We give a thorough analysis of our corpus and show that while the task is not challenging to humans, existing machine comprehension models fail to perform well on the data, even if they make use of a commonsense  ...  We also thank the numerous workers on MTurk for their good work and Carina Silberer and the reviewers for their helpful comments on the paper.  ... 
doi:10.18653/v1/s19-1012 dblp:conf/starsem/OstermannRP19 fatcat:jmkc4lebjzfo7fqrqxc4yxpwfm

English Machine Reading Comprehension Datasets: A Survey [article]

Daria Dzendzik, Carl Vogel, Jennifer Foster
2021 arXiv   pre-print
This paper surveys 60 English Machine Reading Comprehension datasets, with a view to providing a convenient resource for other researchers interested in this problem.  ...  Our analysis reveals that Wikipedia is by far the most common data source and that there is a relative lack of why, when, and where questions across datasets.  ...  We also thank Andrew Dunne, Koel Dutta Chowdhury, Valeriia Filimonova, Victoria Serga, Marina Lisuk, Ke Hu, Joachim Wagner, and Alberto Poncelas.  ... 
arXiv:2101.10421v2 fatcat:xdkiczo3zzdclgbwpxgamvtgwm

Commonsense Knowledge in Word Associations and ConceptNet

Chunhua Liu, Trevor Cohn, Lea Frermann
2021 Proceedings of the 25th Conference on Computational Natural Language Learning   unpublished
RN with ConceptNet on OBQA where p=0.07. 13 See Appendix A for details of 17 and 7 relation types.  ...  This paper presents an in-depth comparison of two large-scale resources of general knowledge: ConceptNet, an engineered relational database, and SWOW a knowledge graph derived from crowd-sourced word associations  ...  We thank the reviewers for their valuable comments, and Simon De Deyne for insightful discussions.  ... 
doi:10.18653/v1/2021.conll-1.38 fatcat:yxwxo5fiova25lg4qykxzkf4sm

Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks

Lisa Bauer, Mohit Bansal
2021 Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   unpublished
We present an approach to assess how well a candidate KG can correctly identify and accurately fill in gaps of reasoning for a task, which we call KG-to-task match.  ...  We show this KGto-task match in 3 phases: knowledge-task identification, knowledge-task alignment, and knowledge-task integration.  ...  This work was supported by DARPA MCS Grant #N66001-19-2-4031, NSF-CAREER Award 1846185, NSF PhD Fellowship, and awards from Microsoft and Amazon.  ... 
doi:10.18653/v1/2021.eacl-main.192 fatcat:srlgycbh3rajlkgvf2fr5jicqq

Relation-aware Bidirectional Path Reasoning for Commonsense Question Answering

Junxing Wang, Xinyi Li, Zhen Tan, Xiang Zhao, Weidong Xiao
2021 Proceedings of the 25th Conference on Computational Natural Language Learning   unpublished
Mcscript2.0: A machine comprehension cor- Haocheng Wu, Zuohui Tian, Wei Wu, and Enhong pus focused on script events and participants. pages Chen. 2017.  ...  The above models are pre- and 72.3% with ELECTRA-large. This indicates trained on a large text corpus and then fine tuned on that the concept representations obtained from the the training data.  ... 
doi:10.18653/v1/2021.conll-1.35 fatcat:b3ev34ntx5dxta5m7lpwfmc2ci