Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Chen Jiangui"'
Autor:
Guo, Jiafeng, Zhou, Changjiang, Zhang, Ruqing, Chen, Jiangui, de Rijke, Maarten, Fan, Yixing, Cheng, Xueqi
Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, e.g., Wikipedia, to produce specific answers. Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, w
Externí odkaz:
http://arxiv.org/abs/2402.16767
Automatic mainstream hashtag recommendation aims to accurately provide users with concise and popular topical hashtags before publication. Generally, mainstream hashtag recommendation faces challenges in the comprehensive difficulty of newly posted t
Externí odkaz:
http://arxiv.org/abs/2312.10466
Autor:
Chen, Jiangui, Zhang, Ruqing, Guo, Jiafeng, de Rijke, Maarten, Chen, Wei, Fan, Yixing, Cheng, Xueqi
Generative retrieval (GR) directly predicts the identifiers of relevant documents (i.e., docids) based on a parametric model. It has achieved solid performance on many ad-hoc retrieval tasks. So far, these tasks have assumed a static document collect
Externí odkaz:
http://arxiv.org/abs/2308.14968
Autor:
Tang, Yubao, Zhang, Ruqing, Guo, Jiafeng, Chen, Jiangui, Zhu, Zuowei, Wang, Shuaiqiang, Yin, Dawei, Cheng, Xueqi
Recently, a new paradigm called Differentiable Search Index (DSI) has been proposed for document retrieval, wherein a sequence-to-sequence model is learned to directly map queries to relevant document identifiers. The key idea behind DSI is to fully
Externí odkaz:
http://arxiv.org/abs/2305.15115
Autor:
Chen, Jiangui, Zhang, Ruqing, Guo, Jiafeng, de Rijke, Maarten, Liu, Yiqun, Fan, Yixing, Cheng, Xueqi
Knowledge-intensive language tasks (KILTs) benefit from retrieving high-quality relevant contexts from large external knowledge corpora. Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic granularity,
Externí odkaz:
http://arxiv.org/abs/2304.14856
Knowledge-intensive language tasks (KILT) usually require a large body of information to provide correct answers. A popular paradigm to solve this problem is to combine a search system with a machine reader, where the former retrieves supporting evid
Externí odkaz:
http://arxiv.org/abs/2208.07652
Fact verification (FV) is a challenging task which aims to verify a claim using multiple evidential sentences from trustworthy corpora, e.g., Wikipedia. Most existing approaches follow a three-step pipeline framework, including document retrieval, se
Externí odkaz:
http://arxiv.org/abs/2204.05511
Question Answering (QA), a popular and promising technique for intelligent information access, faces a dilemma about data as most other AI techniques. On one hand, modern QA methods rely on deep learning models which are typically data-hungry. Theref
Externí odkaz:
http://arxiv.org/abs/2108.05069
Publikováno v:
IEEE Access, Vol 8, Pp 114100-114111 (2020)
GaN devices are developed rapidly in recent years, which makes it possible to produce power electronic converters with higher efficiency and higher power density. However, with the circuit parasitic parameters, large di/dt and dv/dt caused by the GaN
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9ca83f8d845079faceeddfe6f4aaa5e
https://ieeexplore.ieee.org/document/9096274/
https://ieeexplore.ieee.org/document/9096274/
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.