Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Zhangyin Feng"'
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 6514-6528 (2024)
Extracting building heights from single-view remote sensing images greatly enhances the application of remote sensing data. While methods for extracting building height from single-view shadow images have been widely studied, it remains a challenging
Externí odkaz:
https://doaj.org/article/b46436f217e2466ab7a079d5cde60833
Publikováno v:
Mobile Networks and Applications. 25:1722-1728
Machine translation has become an irreplaceable application in the use of mobile phones. However, the current mainstream neural machine translation models depend on continuously increasing the amount of parameters to achieve better performance, which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4bb0bd9dee6f86017d6f780d7b17492
https://doi.org/10.1007/s11036-020-01582-8
https://doi.org/10.1007/s11036-020-01582-8
Whole word masking (WWM), which masks all subwords corresponding to a word at once, makes a better English BERT model. For the Chinese language, however, there is no subword because each token is an atomic character. The meaning of a word in Chinese
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76db9cbf92007b49cdd5fb66beeabda6
http://arxiv.org/abs/2203.00286
http://arxiv.org/abs/2203.00286
Autor:
Zhangyin Feng, Daxin Jiang, Wanjun Zhong, Ming Zhou, Jiahai Wang, Jian Yin, Duyu Tang, Nan Duan, Linjun Shou, Ming Gong
Publikováno v:
ACL
Verifying the correctness of a textual statement requires not only semantic reasoning about the meaning of words, but also symbolic reasoning about logical operations like count, superlative, aggregation, etc. In this work, we propose LogicalFactChec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f61ead49e7a093be97fd970cc6de3e65
http://arxiv.org/abs/2004.13659
http://arxiv.org/abs/2004.13659
Publikováno v:
Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering ISBN: 9783030229672
In this paper, we improve the performance of neural machine translation (NMT) with shallow syntax (e.g., POS tag) of target language, which has better accuracy and latency than deep syntax such as dependency parsing. We present three NMT decoding mod
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9e1148668e0a95f5b1b52c677ebc05aa
https://doi.org/10.1007/978-3-030-22968-9_14
https://doi.org/10.1007/978-3-030-22968-9_14
Publikováno v:
IJCAI
Neural networks have been widely used for high resource language (e.g. English) named entity recognition (NER) and have shown state-of-the-art results.However, for low resource languages, such as Dutch, Spanish, due to the limitation of resources and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::13bb0af055aa4c1f904d708380254ee6
https://doi.org/10.24963/ijcai.2018/566
https://doi.org/10.24963/ijcai.2018/566
Autor:
Duyu Tang, Daya Guo, Ming Zhou, Linjun Shou, Daxin Jiang, Ting Liu, Bing Qin, Zhangyin Feng, Ming Gong, Xiaocheng Feng, Nan Duan
Publikováno v:
Scopus-Elsevier
EMNLP (Findings)
EMNLP (Findings)
We present CodeBERT, a bimodal pre-trained model for programming language (PL) and nat-ural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language codesearch, code documentat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d913a290dcd549844b8672ef3d63f0e
http://www.scopus.com/inward/record.url?eid=2-s2.0-85101859312&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85101859312&partnerID=MN8TOARS