Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Nasrin Mostafazadeh"'
Autor:
Aditya Kalyanpur, Jennifer Chu-Carroll, Or Biran, Lori Moon, Nasrin Mostafazadeh, Lauren Berkowitz, David W. Buchanan
Publikováno v:
EMNLP (1)
When humans read or listen, they make implicit commonsense inferences that frame their understanding of what happened and why. As a step toward AI systems that can build similar mental models, we introduce GLUCOSE, a large-scale dataset of implicit c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::847e0a48556a646c32e4671cd4b38de2
Publikováno v:
ACL (2)
The Story Cloze Test (SCT) is a recent framework for evaluating story comprehension and script learning. There have been a variety of models tackling the SCT so far. Although the original goal behind the SCT was to require systems to perform deep lan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::918378d982472d6d29cce5ceb92b3fab
https://doi.org/10.18653/v1/p18-2119
https://doi.org/10.18653/v1/p18-2119
Publikováno v:
LSDSem@EACL
Mostafazadeh, N, Roth, M, Louis, A, Chambers, N & Allen, J F 2017, LSDSem 2017 Shared Task: The Story Cloze Test . in Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics . pp. 46-51, 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, Valencia, Spain, 3/04/17 . https://doi.org/10.18653/v1/W17-0906
Mostafazadeh, N, Roth, M, Louis, A, Chambers, N & Allen, J F 2017, LSDSem 2017 Shared Task: The Story Cloze Test . in Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics . pp. 46-51, 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, Valencia, Spain, 3/04/17 . https://doi.org/10.18653/v1/W17-0906
The LSDSem’17 shared task is the Story Cloze Test, a new evaluation for story understanding and script learning. This test provides a system with a four-sentence story and two possible endings, and the system must choose the correct ending to the s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2ac07d4148d90a6e084ba8a90fd5981c
https://doi.org/10.18653/v1/w17-0906
https://doi.org/10.18653/v1/w17-0906
Autor:
James F. Allen, Nasrin Mostafazadeh, Pushmeet Kohli, Devi Parikh, Nathanael Chambers, Lucy Vanderwende, Dhruv Batra, Xiaodong He
Publikováno v:
HLT-NAACL
Representation and learning of commonsense knowledge is one of the foundational problems in the quest to enable deep language understanding. This issue is particularly challenging for understanding casual and correlational relationships between event
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3f2dcacba1884518eabfce27e86f221
https://doi.org/10.18653/v1/n16-1098
https://doi.org/10.18653/v1/n16-1098
Autor:
Jacob Devlin, Margaret Mitchell, Nasrin Mostafazadeh, Ishan Misra, Xiaodong He, Lucy Vanderwende
Publikováno v:
ACL (1)
There has been an explosion of work in the vision & language community during the past few years from image captioning to video transcription, and answering questions about images. These tasks have focused on literal descriptions of the image. To mov
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c07c49182b6f166a61eecad7f7f7243
https://doi.org/10.18653/v1/p16-1170
https://doi.org/10.18653/v1/p16-1170
Autor:
Aishwarya Agrawal, Ting-Hao Kenneth Huang, Pushmeet Kohli, C. Lawrence Zitnick, Nasrin Mostafazadeh, Ross Girshick, Jacob Devlin, Dhruv Batra, Lucy Vanderwende, Xiaodong He, Devi Parikh, Francis Ferraro, Margaret Mitchell, Ishan Misra, Michel Galley
Publikováno v:
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND1 v.1, includes 81,743 unique photos in 20,211 sequences, aligned to b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::506d1197984ccaf2a59a09ab3003fae1
https://doi.org/10.18653/v1/n16-1147
https://doi.org/10.18653/v1/n16-1147
Publikováno v:
RepEval@ACL
The main intrinsic evaluation for vector space representation has been focused on textual similarity, where the task is to predict how semantically similar two words or sentences are. We propose a novel framework, Story Cloze Evaluator, for evaluatin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b68f101ef6db1897d24120f8df611380
https://doi.org/10.18653/v1/w16-2505
https://doi.org/10.18653/v1/w16-2505
Publikováno v:
EVENTS@HLT-NAACL
Learning commonsense causal and temporal relation between events is one of the major steps towards deeper language understanding. This is even more crucial for understanding stories and script learning. A prerequisite for learning scripts is a semant
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d59e33aa68545a2e4ac39645a1c45309
https://doi.org/10.18653/v1/w16-1007
https://doi.org/10.18653/v1/w16-1007
Autor:
Nasrin Mostafazadeh, Hector Llorens, James F. Allen, Naushad UzZaman, Nathanael Chambers, James Pustejovsky
Publikováno v:
SemEval@NAACL-HLT
QA TempEval shifts the goal of previous TempEvals away from an intrinsic evaluation methodology toward a more extrinsic goal of question answering. This evaluation requires systems to capture temporal information relevant to perform an end-user task,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c668ce9e76c04876a3a4dff2f875a76b
https://doi.org/10.18653/v1/s15-2134
https://doi.org/10.18653/v1/s15-2134
Autor:
James F. Allen, Nasrin Mostafazadeh
Publikováno v:
Computational Linguistics and Intelligent Text Processing ISBN: 9783319181103
CICLing (1)
CICLing (1)
Natural language understanding is a key requirement for many NLP tasks. Deep language understanding, which enables inference, requires systems that have large amounts of knowledge enabling them to connect natural language to the concepts of the world
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5bef4cd5446f97a7fed03aa261e2c7d5
https://doi.org/10.1007/978-3-319-18111-0_30
https://doi.org/10.1007/978-3-319-18111-0_30