Zobrazeno 1 - 10
of 97
pro vyhledávání: '"Zhu, Yilun"'
Autor:
Liu, Yang Janet, Aoyama, Tatsuya, Scivetti, Wesley, Zhu, Yilun, Behzad, Shabnam, Levine, Lauren Elizabeth, Lin, Jessica, Tiwari, Devika, Zeldes, Amir
Work on shallow discourse parsing in English has focused on the Wall Street Journal corpus, the only large-scale dataset for the language in the PDTB framework. However, the data is not openly available, is restricted to the news domain, and is by no
Externí odkaz:
http://arxiv.org/abs/2411.00491
We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptation, in particular, domain adaptation under posterior drift. We introdu
Externí odkaz:
http://arxiv.org/abs/2411.00079
Singleton mentions, i.e.~entities mentioned only once in a text, are important to how humans understand discourse from a theoretical perspective. However previous attempts to incorporate their detection in end-to-end neural coreference resolution for
Externí odkaz:
http://arxiv.org/abs/2403.17245
Autor:
Zhu, Yilun, Moniz, Joel Ruben Antony, Bhargava, Shruti, Lu, Jiarui, Piraviperumal, Dhivya, Li, Site, Zhang, Yuan, Yu, Hong, Tseng, Bo-Hsiang
Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various domains within
Externí odkaz:
http://arxiv.org/abs/2402.00858
Previous attempts to incorporate a mention detection step into end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention span data as well as other entity information. This paper presents a coreference m
Externí odkaz:
http://arxiv.org/abs/2309.11582
Autor:
Zhu, Yilun, Scott, Clayton, Holland, Darren, Landon, George, Fjeldsted, Aaron, Lintereur, Azaree
Many nuclear safety applications need fast, portable, and accurate imagers to better locate radiation sources. The Rotating Scatter Mask (RSM) system is an emerging device with the potential to meet these needs. The main challenge is the under-determ
Externí odkaz:
http://arxiv.org/abs/2307.15884
Autor:
Aoyama, Tatsuya, Behzad, Shabnam, Gessler, Luke, Levine, Lauren, Lin, Jessica, Liu, Yang Janet, Peng, Siyao, Zhu, Yilun, Zeldes, Amir
We present GENTLE, a new mixed-genre English challenge corpus totaling 17K tokens and consisting of 8 unusual text types for out-of domain evaluation: dictionary entries, esports commentaries, legal documents, medical notes, poetry, mathematical proo
Externí odkaz:
http://arxiv.org/abs/2306.01966
Autor:
Zhu, Yilun, Fjeldsted, Aaron, Holland, Darren, Landon, George, Lintereur, Azaree, Scott, Clayton
Publikováno v:
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42962-42982, 2023
The task of mixture proportion estimation (MPE) is to estimate the weight of a component distribution in a mixture, given observations from both the component and mixture. Previous work on MPE adopts the irreducibility assumption, which ensures ident
Externí odkaz:
http://arxiv.org/abs/2306.01253
Autor:
Žabokrtský, Zdeněk, Konopík, Miloslav, Nedoluzhko, Anna, Novák, Michal, Ogrodniczuk, Maciej, Popel, Martin, Pražák, Ondřej, Sido, Jakub, Zeman, Daniel, Zhu, Yilun
This paper presents an overview of the shared task on multilingual coreference resolution associated with the CRAC 2022 workshop. Shared task participants were supposed to develop trainable systems capable of identifying mentions and clustering them
Externí odkaz:
http://arxiv.org/abs/2209.07841
Autor:
Fjeldsted, Aaron P., Morrow, Tyler J., Scott, Clayton, Zhu, Yilun, Holland, Darren E., Hanks, Ephraim M., Lintereur, Azaree T., Wolfe, Douglas E.
Publikováno v:
In Nuclear Inst. and Methods in Physics Research, A October 2024 1067
