Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Zixia Jia"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:10822-10830
We study graph-based approaches to span-based semantic role labeling. This task is difficult due to the need to enumerate all possible predicate-argument pairs and the high degree of imbalance between positive and negative samples. Based on these dif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd21cb965e334f0fdab18cc298ff3681
https://doi.org/10.1609/aaai.v36i10.21328
https://doi.org/10.1609/aaai.v36i10.21328
Autor:
Xinyu Wang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Kewei Tu
Publikováno v:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef8c672e8e91106156eb8907ece47cfa
https://doi.org/10.18653/v1/2022.naacl-main.232
https://doi.org/10.18653/v1/2022.naacl-main.232
Publikováno v:
Findings of the Association for Computational Linguistics: NAACL 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7338cc8a582a923885faec6a90d27787
https://doi.org/10.18653/v1/2022.findings-naacl.71
https://doi.org/10.18653/v1/2022.findings-naacl.71
Publikováno v:
Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021).
This paper describes the system used in submission from SHANGHAITECH team to the IWPT 2021 Shared Task. Our system is a graph-based parser with the technique of Automated Concatenation of Embeddings (ACE). Because recent work found that better word r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::122982e83befc427c37230f76bdb802d
https://doi.org/10.18653/v1/2021.iwpt-1.20
https://doi.org/10.18653/v1/2021.iwpt-1.20
Autor:
Tao Wang, Yong Jiang, Nguyen Bach, Kewei Tu, Zixia Jia, Zhongqiang Huang, Xinyu Wang, Fei Huang, Zhaohui Yan
Publikováno v:
ACL/IJCNLP (1)
Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the cross-entropy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b5fbffb4ce0628f06c01d9d4eb96808
http://arxiv.org/abs/2010.05010
http://arxiv.org/abs/2010.05010
Publikováno v:
ACL
Semantic dependency parsing, which aims to find rich bi-lexical relationships, allows words to have multiple dependency heads, resulting in graph-structured representations. We propose an approach to semi-supervised learning of semantic dependency pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e0730ceeecd54353ca1e272c109ca813
https://doi.org/10.18653/v1/2020.acl-main.607
https://doi.org/10.18653/v1/2020.acl-main.607
Publikováno v:
CoNLL Shared Task
This paper presents the system used in our submission to the \textit{CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing}. Our system is a graph-based parser which combines an extended pointer-generator network that generates nodes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89387e85bddf3d2c65d486d0569cf7a3
https://doi.org/10.18653/v1/k19-2005
https://doi.org/10.18653/v1/k19-2005