Zobrazeno 1 - 10
of 103
pro vyhledávání: '"Jackie Chi Kit Cheung"'
Autor:
Samira Abbasgholizadeh Rahimi, Mehdi Mousavi, Shabnam Shafiee, Jason M Harley, Jackie Chi Kit Cheung
Publikováno v:
Family Medicine and Community Health, Vol 12, Iss Suppl 1 (2024)
Externí odkaz:
https://doaj.org/article/b6c4e32a4c1848cd83543a9c812d4a3a
Publikováno v:
AAAI
Summaries of fictional stories allow readers to quickly decide whether or not a story catches their interest. A major challenge in automatic summarization of fiction is the lack of standardized evaluation methodology or high-quality datasets for expe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::82b3ca1ec1dd82a22fc50eee4bfe5f8e
https://doi.org/10.1609/aaai.v33i01.33017476
https://doi.org/10.1609/aaai.v33i01.33017476
Autor:
Akshatha Arodi, Jackie Chi Kit Cheung
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0650058084968a05a8531d10c289ef2b
https://doi.org/10.18653/v1/2021.findings-emnlp.351
https://doi.org/10.18653/v1/2021.findings-emnlp.351
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e2222d00f8338104782ccb013b2be66a
https://doi.org/10.18653/v1/2021.findings-emnlp.359
https://doi.org/10.18653/v1/2021.findings-emnlp.359
Autor:
Ian Porada, Adam Trischler, Alexandra Olteanu, Kaheer Suleman, Ali Emami, Jackie Chi Kit Cheung
Publikováno v:
ACL/IJCNLP (1)
A false contract is more likely to be rejected than a contract is, yet a false key is less likely than a key to open doors. While correctly interpreting and assessing the effects of such adjective-noun pairs (e.g., false key) on the plausibility of g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21b8e196f12c69bbdac1ce6294787c94
https://doi.org/10.18653/v1/2021.acl-long.553
https://doi.org/10.18653/v1/2021.acl-long.553
Autor:
Chandra Bhagavatula, Yejin Choi, Jackie Chi Kit Cheung, Antoine Bosselut, Ximing Lu, Jena D. Hwang, Yue Dong
Publikováno v:
ACL/IJCNLP (Findings)
Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the generated text is repetitive, generic, self-contradictory, and often lacks commonsense. Our analyses on sentence-lev
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f20037aadaa6be7c85c916a1544cb6b
https://doi.org/10.18653/v1/2021.findings-acl.107
https://doi.org/10.18653/v1/2021.findings-acl.107
Publikováno v:
NAACL-HLT
Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events. While distributional models -- most recently pre-trained, Transformer language models -- have demonstrated improvements in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82ecaebf6e43253114c8559e99eba0a2
Publikováno v:
EACL
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents. Our method assumes a two-level hierarchical graph representation of the source document, and exploits asymmetrical positional cues to dete
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5a4c62cee659522c3e7f292f4a0b78ed
https://doi.org/10.18653/v1/2021.eacl-main.93
https://doi.org/10.18653/v1/2021.eacl-main.93
Autor:
Jad Kabbara, Jackie Chi Kit Cheung
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf1ddec422d2fd3ae5a3f079557a9ddf
https://doi.org/10.18653/v1/2021.findings-emnlp.312
https://doi.org/10.18653/v1/2021.findings-emnlp.312
Autor:
Wei Yang, Peng Xu, Wenjie Zi, Dhruv Kumar, Yanshuai Cao, Chenyang Huang, Jackie Chi Kit Cheung, Simon J. D. Prince, Keyi Tang
Publikováno v:
ACL/IJCNLP (1)
It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work shows tha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::495e0d00c34090ca4bba8379be67e693
http://arxiv.org/abs/2012.15355
http://arxiv.org/abs/2012.15355