Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Peiyang, Liu"'
Publikováno v:
2022 3rd International Conference on Computer Vision, Image and Deep Learning & International Conference on Computer Engineering and Applications (CVIDL & ICCEA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b9921ec3289b9291fc10db4d2d97d7a
https://doi.org/10.1109/cvidliccea56201.2022.9825095
https://doi.org/10.1109/cvidliccea56201.2022.9825095
Publikováno v:
CIKM
Distilled BERT models are more suitable for efficient vertical retrieval in online sponsored vertical search with low-latency requirements than BERT due to fewer parameters and faster inference. Unfortunately, most of these models are still far from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0b674f8d0a00304477d11917bea16c2d
https://doi.org/10.1145/3459637.3481909
https://doi.org/10.1145/3459637.3481909
Publikováno v:
Materials; Volume 15; Issue 22; Pages: 7998
In this research, experimental research and finite element modelling of glulam-concrete composite (GCC) beams were undertaken to study the flexural properties of composite beams containing timber board interlayers. The experimental results demonstrat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5eac6b5775f64f3c902c67b29d532d63
https://doi.org/10.3390/ma15227998
https://doi.org/10.3390/ma15227998
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a89bf8ad6d474cc9617abaf131206a73
https://doi.org/10.18653/v1/2021.findings-emnlp.13
https://doi.org/10.18653/v1/2021.findings-emnlp.13
Publikováno v:
NAACL-HLT
The embedding-based large-scale query-document retrieval problem is a hot topic in the information retrieval (IR) field. Considering that pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, we present a Q
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0dcde481e24fb544b4f60bfe16931960
https://doi.org/10.18653/v1/2021.naacl-main.292
https://doi.org/10.18653/v1/2021.naacl-main.292
Publikováno v:
IJCNN
Traditional word embedding approaches learn semantic information from the associated contexts of words on large unlabeled corpora, which ignores a fact that synonymy between words happens often within different contexts in a corpus, so this relations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79a7af94d1d5e6646c5b7f80da79868e
https://doi.org/10.1109/ijcnn48605.2020.9207311
https://doi.org/10.1109/ijcnn48605.2020.9207311
Publikováno v:
Optical Transmission Systems, Subsystems, and Technologies.
The purpose of this paper is to numerically study performance improvement of single-channel secure chaotic optical communications utilizing symmetrical dispersion compensation technique. The decrypted 1.25-Gbits/s non-return-tozero (NRZ) sequence at
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b8fc4dd1ec3dfcec03b6da35f67794d0
https://doi.org/10.1364/acp.2011.83092e
https://doi.org/10.1364/acp.2011.83092e