Zobrazeno 1 - 10
of 313
pro vyhledávání: '"Zhang, YuanKai"'
An important line of research in the field of explainability is to extract a small subset of crucial rationales from the full input. The most widely used criterion for rationale extraction is the maximum mutual information (MMI) criterion. However, i
Externí odkaz:
http://arxiv.org/abs/2410.06003
Rationalization models, which select a subset of input text as rationale-crucial for humans to understand and trust predictions-have recently emerged as a prominent research area in eXplainable Artificial Intelligence. However, most of previous studi
Externí odkaz:
http://arxiv.org/abs/2408.10795
Autor:
Pathiravasan, Chathurangi H, Zhang, Yuankai, Trinquart, Ludovic, Benjamin, Emelia J, Borrelli, Belinda, McManus, David D, Kheterpal, Vik, Lin, Honghuang, Sardana, Mayank, Hammond, Michael M, Spartano, Nicole L, Dunn, Amy L, Schramm, Eric, Nowak, Christopher, Manders, Emily S, Liu, Hongshan, Kornej, Jelena, Liu, Chunyu, Murabito, Joanne M
Publikováno v:
Journal of Medical Internet Research, Vol 23, Iss 1, p e24773 (2021)
BackgroundeCohort studies offer an efficient approach for data collection. However, eCohort studies are challenged by volunteer bias and low adherence. We designed an eCohort embedded in the Framingham Heart Study (eFHS) to address these challenges a
Externí odkaz:
https://doaj.org/article/f6819a15ea004bedbbac24e3eb73074e
Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions based on
Externí odkaz:
http://arxiv.org/abs/2312.04103
Rationalization is a self-explaining framework for NLP models. Conventional work typically uses the maximum mutual information (MMI) criterion to find the rationale that is most indicative of the target label. However, this criterion can be influence
Externí odkaz:
http://arxiv.org/abs/2309.13391
Autor:
Liu, Wei, Wang, Jun, Wang, Haozhao, Li, Ruixuan, Qiu, Yang, Zhang, YuanKai, Han, Jie, Zou, Yixiong
A self-explaining rationalization model is generally constructed by a cooperative game where a generator selects the most human-intelligible pieces from the input text as rationales, followed by a predictor that makes predictions based on the selecte
Externí odkaz:
http://arxiv.org/abs/2305.13599
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor. However, rationalization suffers from
Externí odkaz:
http://arxiv.org/abs/2305.04492
Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces. However, such a two-phase model may incur the degeneration prob
Externí odkaz:
http://arxiv.org/abs/2209.08285
Publikováno v:
In Journal of Hazardous Materials 5 August 2024 474
Publikováno v:
In Chemical Engineering Research and Design August 2024 208:464-474