Development and validation of a prognostic model of survival for classic heatstroke patients: a multicenter study

Autor: Yu Wang, Donglin Li, Zongqian Wu, Chuan Zhong, Shengjie Tang, Haiyang Hu, Pei Lin, Xianqing Yang, Jiangming Liu, Xinyi He, Haining Zhou, Fake Liu

Publikováno v: Scientific Reports, Vol 13, Iss 1, Pp 1-12 (2023)

Abstract Classic heatstroke (CHS) is a life-threatening illness characterized by extreme hyperthermia, dysfunction of the central nervous system and multiorgan failure. Accurate predictive models are useful in the treatment decision-making process an

Externí odkaz: https://doaj.org/article/3efb1f411d9246cebf150559a5805b68

In-Order Transition-based Constituent Parsing

Autor: Jiangming Liu, Yue Zhang

Publikováno v: Transactions of the Association for Computational Linguistics, Vol 5 (2021)

Externí odkaz: https://doaj.org/article/b1d968b046bd457fbbc0c4eb3afbbd8d

Text Generation from Discourse Representation Structures

Autor: Shay B. Cohen, Jiangming Liu, Mirella Lapata

Publikováno v: Liu, J, Cohen, S B & Lapata, M 2021, Text Generation from Discourse Representation Structures . in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . Online, pp. 397-415, 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 6/06/21 . https://doi.org/10.18653/v1/2021.naacl-main.35
NAACL-HLT

We propose neural models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs). DRSs are document-level representations which encode rich semantic detail pertaining to rhetorical relations, presuppos

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d40e04d7270f0f5b018b68348fe5181f
https://hdl.handle.net/20.500.11820/135652fe-1b20-442d-a62c-64693be6d773

Shift-Reduce Constituent Parsing with Neural Lookahead Features

Autor: Jiangming Liu, Yue Zhang

Publikováno v: Transactions of the Association for Computational Linguistics. 5:45-58

Transition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which consists of a sequence of non-local constituents. O

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f6e59d34edfadabaab4a8dcde1f63a8
https://doi.org/10.1162/tacl_a_00045

Discourse Representation Parsing for Sentences and Documents

Autor: Shay B. Cohen, Mirella Lapata, Jiangming Liu

Publikováno v: ACL (1)

We introduce a novel semantic parsing task based on Discourse Representation Theory (DRT; Kamp and Reyle 1993). Our model operates over Discourse Representation Tree Structures which we formally define for sentences and documents. We present a genera

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::710dfd69c235198edd0f54aa7a18b4c6
https://doi.org/10.18653/v1/p19-1629