Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Yuning Mao"'
Autor:
Huajie Shao, Tarek Abdelzaher, Jiawei Han, Minhao Jiang, Yuning Mao, Yu Meng, Wenda Qiu, Dachun Sun, Ruijie Wang, Chaoqi Yang, Zhenzhou Yang, Xinyang Zhang, Yu Zhang, Sam Cohen, James Flamino, Gyorgy Korniss, Omar Malik, Aamir Mandviwalla, Boleslaw Szymanski, Lake Yin
Publikováno v:
2021 Winter Simulation Conference (WSC).
Publikováno v:
Journal of Alloys and Compounds. 803:224-230
Wide attention has been recently paid to the potential application of nanosized SnO2 material in lithium-ion batteries as a new high performance anode owe to its high theoretical specific capacity and moderate working potential. However, the intrinsi
Stepping from sentence-level to document-level, the research on relation extraction (RE) confronts increasing text length and more complicated entity interactions. Consequently, it is more challenging to encode the key information sources--relevant c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f551557e7114b952a96bb5c61d3360c
http://arxiv.org/abs/2109.12093
http://arxiv.org/abs/2109.12093
Publikováno v:
Journal of Alloys and Compounds. 784:125-133
As the concept of promoting environmental protection and energy conservation becomes more and more popular, reasonably green approaches for preparing high-performance nanostructured Fe2O3 anodes will be well received. Herein, porous Fe2O3 quasi-clust
Publikováno v:
ACL/IJCNLP (1)
We propose Generation-Augmented Retrieval (GAR) for answering open-domain questions, which augments a query through text generation of heuristically discovered relevant contexts without external resources as supervision. We demonstrate that the gener
Publikováno v:
Proceedings of the 2021 SIAM International Conference on Data Mining (SDM) ISBN: 9781611976700
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b710d6d53071c6142dbe6615652d20b
https://doi.org/10.1137/1.9781611976700.54
https://doi.org/10.1137/1.9781611976700.54
Prior studies on text-to-text generation typically assume that the model could figure out what to attend to in the input and what to include in the output via seq2seq learning, with only the parallel training data and no additional guidance. However,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::94da8e99047768733eb8be85d176c359
Publikováno v:
ACL/IJCNLP (Findings)
Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose a simple
Autor:
Yaqing Wang, Yan Liang, Surender Pal Singh, Yifan Ethan Xu, Fan Xiao, Andrew McCallum, Xian Li, Jiawei Han, Xiang He, Jun Ma, Chenwei Zhang, Alexandre Michetti Manduca, Xin Luna Dong, Yuning Mao, Saurabh Deshpande, Andrey Kan, Giannis Karamanolakis, Jay Ren, Gabriel Blanco Saldana, Tong Zhao, Christos Faloutsos, Haw-Shiuan Chang
Publikováno v:
KDD
Can one build a knowledge graph (KG) for all products in the world? Knowledge graphs have firmly established themselves as valuable sources of information for search and question answering, and it is natural to wonder if a KG can contain information
Publikováno v:
EMNLP (1)
Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions. However, the sparse reward signals offered by the KG during traversal are often insufficient to g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04792b3cdfffcfbf147970395f384148