search

declare-lab / RelationPrompt

This repository implements our ACL Findings 2022 research paper RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction. The goal of Zero-Shot Relation Triplet Extraction (ZeroRTE) is to extract relation triplets of the format (head entity, tail entity, relation), despite not having annotated data for the test relation labels.
MIT License
122 stars 16 forks source link

有支持中文的模型吗 #12

Open Rick-24 opened 1 year ago

Rick-24 commented 1 year ago

有支持中文的模型吗

chiayewken commented 1 year ago

Hi, you can change the pretrained models to Chinese version in the training stage:

eg "gpt2" -> "ckiplab/gpt2-base-chinese" eg "facebook/bart-base" -> "fnlp/bart-base-chinese"

Rick-24 commented 1 year ago

您好，您的来信我已收到，我会尽快处理。      祝好！

Rick-24 commented 1 year ago

Thank you very much！

GitHubwwZ commented 7 months ago

Hi, you can change the pretrained models to Chinese version in the training stage:

eg "gpt2" -> "ckiplab/gpt2-base-chinese" eg "facebook/bart-base" -> "fnlp/bart-base-chinese"

请问有支持中文训练的数据集嘛？

Rick-24 commented 7 months ago

您好，您的来信我已收到，我会尽快处理。      祝好！

GitHubwwZ commented 7 months ago

有支持中文的模型吗

方便添加一下您的联系方式，和您探讨一下中文关系三元组抽取任务嘛？ 谢谢啦～