Code Monkey home page Code Monkey logo

sentiprompt's People

Contributors

mrzixi avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

sentiprompt's Issues

实验结果差距很大,请问是什么原因?

您好,以下是我使用本仓库代码替换随机种子重复5次跑出的实验结果,感觉实验结果与论文中汇报的结果差距有点大,请问能提供一下详细的训练命令代码吗?

task="penga/14lap penga/14res penga/15res penga/16res pengb/14lap pengb/14res pengb/15res pengb/16res lcx/14lap lcx/14res lcx/15res lcx/16res"
s="544 3210 8 5678 744"
for SEED in $s
do
for dataset in $task
do
LOG_DIR=/mnt/f/yj/senti/logs_prompt_type3bs16/$dataset/$SEED
python train.py --dataset_name $dataset \
                                       --log_dir $LOG_DIR \
                                       --batch_size 32 \
                                       --lr 5e-5 \
                                       --n_epochs 50 \
                                       --save_model $LOG_DIR/models \
                                       --prompt type3 \
                                       --seed $SEED
done
done
ds test_aesc_f1_mean test_pair_f1_mean test_f1_mean test_precision_mean test_recall_mean
penga_14lap 65.3 58.59 54.48 64.43 47.2
penga_14res 76.19 74.02 69.96 72.69 67.42
penga_15res 66.32 64.76 55.55 61.7 50.51
penga_16res 74.94 72.99 67.89 70.64 65.36
ds test_aesc_f1_mean test_pair_f1_mean test_f1_mean test_precision_mean test_recall_mean
pengb_14lap 68.42 61.09 55.25 60.22 51.04
pengb_14res 78.59 72.26 69.01 70.61 67.49
pengb_15res 67.19 62.19 53.49 59.96 48.29
pengb_16res 73.11 70.07 65.8 70.94 61.37
ds test_aesc_f1_mean test_pair_f1_mean test_f1_mean test_precision_mean test_recall_mean
lcx_14lap 67.12 55.59 51.64 57.75 46.7
lcx_14res 75.56 64.84 60.99 63.45 58.73
lcx_15res 68.63 56.04 51.25 55.15 47.88
lcx_16res 76.25 68.69 64.06 67.66 60.83

关于最新版本的代码

您好,我阅读了您的论文,觉得您的想法十分具有创造性和启发性,所以我想深入阅读您的具体代码。但是我运行了代码,发现跑出来的结果和论文中报告的差距比较大。希望您可以公布最新版本的代码。感谢您的工作。

关于代码

您好,请问什么时候可以把代码开源呢?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.