Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Keisuke Sakaguchi"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 4 (2021)
Externí odkaz:
https://doaj.org/article/739c09c7bbe249b797bb6dc70fffa06c
Autor:
Keisuke Sakaguchi1 keisukes@allenai.org, Le Bras, Ronan1 ronanlb@allenai.org, Bhagavatula, Chandra1 chandrab@allenai.org, Yejin Choi2 yejin@cs.washington.edu
Publikováno v:
Communications of the ACM. Sep2021, Vol. 64 Issue 9, p99-106. 8p. 2 Diagrams, 8 Charts.
Autor:
Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, Yejin Choi
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:6384-6392
Recent years have brought about a renewed interest in commonsense representation and reasoning in the field of natural language understanding. The development of new commonsense knowledge graphs (CSKG) has been central to these advances as their dive
Autor:
Jungo Kasai, Keisuke Sakaguchi, Lavinia Dunagan, Jacob Morrison, Ronan Le Bras, Yejin Choi, Noah Smith
We establish THumB, a rubric-based human evaluation protocol for image captioning models. Our scoring rubrics and their definitions are carefully developed based on machine- and human-generated captions on the MSCOCO dataset. Each caption is evaluate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f249588ea46fb8c153598844e2634d05
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Autor:
Jungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Lavinia Dunagan, Jacob Morrison, Alexander Fabbri, Yejin Choi, Noah Smith
Natural language processing researchers have identified limitations of evaluation methodology for generation tasks, with new questions raised about the validity of automatic metrics and of crowdworker judgments. Meanwhile, efforts to improve generati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4b361d552f539ef20e5dc8f03f4473e6
Autor:
Keisuke Sakaguchi, Niket Tandon, Dheeraj Rajagopal, Kyle Richardson, Michal Guerquin, Eduard Hovy, Peter Clark, Bhavana Dalvi
Publikováno v:
EMNLP (1)
We present the first dataset for tracking state changes in procedural text from arbitrary domains by using an unrestricted (open) vocabulary. For example, in a text describing fog removal using potatoes, a car window may transition between being fogg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b6d710b074b28732b812195a3ea6a22
http://arxiv.org/abs/2011.08092
http://arxiv.org/abs/2011.08092
Autor:
Takuya Sumiyama, Kenichi Furukawa, Hiroshi Enomoto, Mitsuharu Kan, Tsuyoshi Matsuo, Keisuke Sakaguchi
Publikováno v:
Composite Structures. 181:368-378
The structural beams with a uniform cross section of hat-shape were manufactured through a high-cycle compression molding technique, by using randomly oriented chopped thermoplastic composites. The crash tubes were obtained by vibration welding of th
Autor:
Ryo Nagata, Keisuke Sakaguchi
Publikováno v:
ACL (1)
Publikováno v:
EMNLP/IJCNLP (1)
We introduce WIQA, the first large-scale dataset of "What if..." questions over procedural text. WIQA contains three parts: a collection of paragraphs each describing a process, e.g., beach erosion; a set of crowdsourced influence graphs for each par