Yu Wu, Yue Zhang, Sen Yang, Leyang Cui, Jian Liu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
There is a recent interest in investigating fewshot NER, where the low-resource target domain has different label sets compared with a resource-rich source domain. Existing methods use a similarity-based metric. However, they cannot make full use of knowledge transfer in NER model parameters. To address the issue, we propose a template-based method for NER, treating NER as a language model ranking problem in a sequence-to-sequence framework, where original sentences and statement templates filled by candidate named entity span are regarded as the source sequence and the target sequence, respectively. For inference, the model is required to classify each candidate span based on the corresponding template scores. Our experiments demonstrate that the proposed method achieves 92.55% F1 score on the CoNLL03 (rich-resource task), and significantly better than fine-tuning BERT 10.88%, 15.34%, and 11.73% F1 score on the MIT Movie, the MIT Restaurant, and the ATIS (low-resource task), respectively.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.01760")
get_code_for_paper("2106.01760")
have("2106.01760")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.01760.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.01760)
Connect an agent — have() is free.