Yilun Zhu — accepted AI-conference papers

2024

GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domains

Yang Janet Liu, Tatsuya Aoyama, Wesley Scivetti, Yilun Zhu, Shabnam Behzad, Lauren Elizabeth Levine +3

EMNLP 2024main

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 now 35 years old. In this paper, we present and eval…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Label Noise: Ignorance Is Bliss

Yilun Zhu, Jianxin Zhang, Aditya Gangrade, Clayton Scott

NeurIPS 2024poster

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 introduce the concept of \emph{relative…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolution

Yilun Zhu, Siyao Peng, Sameer Pradhan, Amir Zeldes

COLING 2024main

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 English have been hampered by the lack of singlet…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Mixture Proportion Estimation Beyond Irreducibility

Yilun Zhu, Aaron Fjeldsted, Darren Holland, George Landon, Azaree Lintereur, Clayton Scott

ICML 2023poster

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 identifiablity of the mixture proportion. In this pap…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2021

OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres

Yilun Zhu, Sameer Pradhan, Amir Zeldes

ACL 2021short

SOTA coreference resolution produces increasingly impressive scores on the OntoNotes benchmark. However lack of comparable data following the same scheme for more genres makes it difficult to evaluate generalizability to open domain data. This paper provides a dataset and comprehensive evaluation sh…

Cited by 24 Source ↗PDF ↗code ↗Scholar ↗