Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Xunlin Zhan"'
Publikováno v:
IEEE Transactions on Multimedia. :1-13
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c58c82a701a6d24b1f61577b71e89ec
https://doi.org/10.1109/tmm.2022.3222653
https://doi.org/10.1109/tmm.2022.3222653
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:6375-6383
When answering a question, people often draw upon their rich world knowledge in addition to the particular context. While recent works retrieve supporting facts/evidence from commonsense knowledge bases to supply additional information to each questi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a73ee11b0d952f5d63f9d04cf0afaa7e
https://doi.org/10.1609/aaai.v35i7.16791
https://doi.org/10.1609/aaai.v35i7.16791
Commonsense question answering requires reasoning about everyday situations and causes and effects implicit in context. Typically, existing approaches first retrieve external evidence and then perform commonsense reasoning using these evidence. In th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d056f7854aaf321e636115eb053ea056
Autor:
Xiao Dong, Xunlin Zhan, Yangxin Wu, Yunchao Wei, Michael C. Kampffmeyer, Xiaoyong Wei, Minlong Lu, Yaowei Wang, Xiaodan Liang
Despite the potential of multi-modal pre-training to learn highly discriminative feature representations from complementary data modalities, current progress is being slowed by the lack of large-scale modality-diverse datasets. By leveraging the natu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6410d2e17d55d05c1c0abcbed01a5cf
http://arxiv.org/abs/2109.04275
http://arxiv.org/abs/2109.04275
Publikováno v:
Knowledge-Based Systems. 235:107612
Commonsense question answering has attracted increasing attention as a challenging task requiring the human reasoning process of answering questions with the help of abundant commonsense knowledge. Existing methods mostly resort to large pre-trained
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::19e20220489c47532cfde79c7020b574
https://doi.org/10.1016/j.knosys.2021.107612
https://doi.org/10.1016/j.knosys.2021.107612