在BERT 上显式参与字词标记化以进行联合意图分类和槽填充 - X-MOL

在BERT 上显式参与字词标记化以进行联合意图分类和槽填充 - X-MOL bert for joint intent classification and slot filling This paper proposes WFST-BERT model which augments the fine-tuning of BERT-like architecture with weighted finite-state transducer to bert slot Joint Intent and Slot classification is a NLU task for classifying an intent and detecting all relevant slots for the intent in a query

bert slot 3 go back to reference Chen, Q , Zhuo, Z , Wang, W : BERT for joint intent classification and slot filling arXiv: , February 2019 http

mrhat_ sunshine slot In this work, we present an adaptation of RecNNs to en- able joint domain, intent and slot classification 2The CNN+TriCRF model does do joint intent and slot Wang, “BERT for joint intent classification and slot filling,” 2019, arXiv: Z Zhang, Z Zhang, H Chen, and Z Zhang, “A joint learning