Yiding Tan — accepted AI-conference papers

2022

Searching for Optimal Subword Tokenization in Cross-domain NER

Ruotian Ma, Yiding Tan, Xin Zhou, Xuanting Chen, Di Liang, Sirui Wang +2

IJCAI 2022poster

Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA). The most popular UDA approaches focus on domain-invariant representation learning, trying to align the features from different domains into a similar feature distribution. However, these approaches ignore…

Cited by 14 Source ↗PDF ↗code ↗Scholar ↗

2022

Template-free Prompt Tuning for Few-shot NER

Ruotian Ma, Xin Zhou, Tao Gui, Yiding Tan, Linyang Li, Qi Zhang +1

NAACL 2022long

Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words. However, when applied to token-level labeling tasks such as NER, it would be time-consuming to enumerate the template queries over all…

Cited by 207 Source ↗PDF ↗code ↗Scholar ↗